
from pprint import pprint
import numpy as np
import pandas as pd

# Libraries to help with data visualization
import matplotlib.pyplot as plt
import seaborn as sns
import plotly.express as px
from IPython.core.display import display

#preprocessing for model
from sklearn.preprocessing import StandardScaler, MinMaxScaler, RobustScaler, Normalizer
import sklearn.metrics as metrics
from sklearn.model_selection import train_test_split

#tensorflow libraries
import tensorflow as tf

from tensorflow import keras
from tensorflow.keras import Sequential
from tensorflow.keras.layers import Dense, Dropout
from tensorflow.keras.metrics import Precision, Recall, BinaryAccuracy

INFO:tensorflow:Enabling eager execution
INFO:tensorflow:Enabling v2 tensorshape
INFO:tensorflow:Enabling resource variables
INFO:tensorflow:Enabling tensor equality
INFO:tensorflow:Enabling control flow v2


# Utility Functions

#Function to make a summary df to aid EDA
def make_summary_cols(df, cat_threshold=20):
    '''Create a df to summarise the data df based on dtypes, nulls, numeric or not, categorical or not

    df: data threshold
    cat_threshold: number of unique types below which assume categorical

    returns:
    summary_cols: df of summary
    d: dict of column names where keys are numeric_cols, categorical_cols and non_numeric_cols where
    values against the keys contain corresponding column names
    '''
    types = df.dtypes
    types.name = 'col_types'

    nuniques = data.nunique()
    nuniques.name = 'n_uniques'

    nulls = df.isnull().sum()
    nulls.name = 'nulls'

    summary_cols = pd.merge(left=pd.merge(left=nuniques, right=types, left_index=True, right_index=True), right=nulls,\
                            left_index=True, right_index=True).sort_values(by='col_types')
    summary_cols['isnumeric_column'] = summary_cols['col_types'].apply(lambda x: False if x=='object' else True)

    summary_cols['probably_categorical'] = summary_cols['n_uniques'].apply(lambda x: True if x <=cat_threshold \
        else False)

    d = {
        'numeric_cols': list(summary_cols[summary_cols.isnumeric_column==True].index),
        'categorical_cols': list(summary_cols[summary_cols.probably_categorical==True].index),
        'non_numeric_cols': list(summary_cols[summary_cols.isnumeric_column==False].index)
    }

    return summary_cols, d

#Plot histogram and boxplot together
def histogram_boxplot(feature, figsize=(15,10), bins = None):
    """ Boxplot and histogram combined
    feature: 1-d feature array
    figsize: size of fig (default (9,8))
    bins: number of bins (default None / auto)
    """
    f2, (ax_box2, ax_hist2) = plt.subplots(nrows = 2, # Number of rows of the subplot grid= 2
                                           sharex = True, # x-axis will be shared among all subplots
                                           gridspec_kw = {"height_ratios": (.25, .75)}, 
                                           figsize = figsize 
                                           ) # creating the 2 subplots
    sns.boxplot(x=feature, ax=ax_box2, showmeans=True, color='violet') # boxplot will be created and a star will indicate the mean value of the column
    sns.histplot(x=feature, kde=True, ax=ax_hist2, bins=bins,palette="winter") if bins else sns.histplot(x=feature, kde=True, ax=ax_hist2) # For histogram
    ax_hist2.axvline(np.mean(feature), color='green', linestyle='--') # Add mean to the histogram
    ax_hist2.axvline(np.median(feature), color='black', linestyle='-') # Add median to the histogram

#Plot confusion matrix
def make_confusion_matrix(model, y_actual, y_predict=None, labels=[1, 0], cmap='Blues'):
    '''
    model : classifier to predict values of X
    y_actual : ground truth  
    
    '''
    if y_predict is None:
        y_predict = model.predict(X_test)

    cm=metrics.confusion_matrix(y_actual, y_predict, labels=[0, 1])
    df_cm = pd.DataFrame(cm, index = [i for i in ["Actual - No","Actual - Yes"]],
                  columns = [i for i in ['Predicted - No','Predicted - Yes']])
    group_counts = ["{0:0.0f}".format(value) for value in
                cm.flatten()]
    group_percentages = ["{0:.2%}".format(value) for value in
                         cm.flatten()/np.sum(cm)]
    labels = [f"{v1}\n{v2}" for v1, v2 in
              zip(group_counts,group_percentages)]
    labels = np.asarray(labels).reshape(2,2)
    plt.figure(figsize = (10,7))
    sns.heatmap(df_cm, annot=labels,fmt='', cmap=cmap)
    plt.ylabel('True label')
    plt.xlabel('Predicted label')
    
# Function to add data labels to bar plots
def show_values_on_bars(axs):
    def _show_on_single_plot(ax):        
        for p in ax.patches:
            _x = p.get_x() + p.get_width() / 2
            _y = p.get_y() + p.get_height()
            value = '{:.2f}'.format(p.get_height())
            ax.text(_x, _y, value, ha="center") 

    if isinstance(axs, np.ndarray):
        for idx, ax in np.ndenumerate(axs):
            _show_on_single_plot(ax)
    else:
        _show_on_single_plot(axs)


data = pd.read_csv('bank.csv')


data.head()


data.shape

(10000, 14)


data.isnull().sum()

RowNumber          0
CustomerId         0
Surname            0
CreditScore        0
Geography          0
Gender             0
Age                0
Tenure             0
Balance            0
NumOfProducts      0
HasCrCard          0
IsActiveMember     0
EstimatedSalary    0
Exited             0
dtype: int64


data.nunique()

RowNumber          10000
CustomerId         10000
Surname             2932
CreditScore          460
Geography              3
Gender                 2
Age                   70
Tenure                11
Balance             6382
NumOfProducts          4
HasCrCard              2
IsActiveMember         2
EstimatedSalary     9999
Exited                 2
dtype: int64


data.dtypes

RowNumber            int64
CustomerId           int64
Surname             object
CreditScore          int64
Geography           object
Gender              object
Age                  int64
Tenure               int64
Balance            float64
NumOfProducts        int64
HasCrCard            int64
IsActiveMember       int64
EstimatedSalary    float64
Exited               int64
dtype: object


data.describe().T


data.describe(include=['object']).T


# Creating new df dropping unnecessary columns
working_df = data.drop(['RowNumber','CustomerId','Surname'], axis=1)


# create lists of columns by type
summary_df, d = make_summary_cols(working_df)

numeric_cols = d['numeric_cols']
categorical_cols = d['categorical_cols']
non_numeric_cols = d['non_numeric_cols']

numeric_cols.sort()
categorical_cols.sort()
non_numeric_cols.sort()

summary_df


print(f'numeric cols are: \n {numeric_cols}\n')
print(f'categorical cols (defined as <= 20 uniques) are: \n {categorical_cols}\n')
print(f'non numeric cols are: \n {non_numeric_cols}')

numeric cols are: 
 ['Age', 'Balance', 'CreditScore', 'EstimatedSalary', 'Exited', 'HasCrCard', 'IsActiveMember', 'NumOfProducts', 'Tenure']

categorical cols (defined as <= 20 uniques) are: 
 ['Exited', 'Gender', 'Geography', 'HasCrCard', 'IsActiveMember', 'NumOfProducts', 'Tenure']

non numeric cols are: 
 ['Gender', 'Geography']


histogram_boxplot(working_df.CreditScore)


px.box(working_df.CreditScore, orientation='h', height=200)


px.histogram(working_df.CreditScore)


working_df.CreditScore.describe()

count    10000.000000
mean       650.528800
std         96.653299
min        350.000000
25%        584.000000
50%        652.000000
75%        718.000000
max        850.000000
Name: CreditScore, dtype: float64


histogram_boxplot(working_df.Age)


px.box(working_df.Age, orientation='h', height=200)


print(f'No. of rows with age > 62: {working_df[working_df.Age>62].count()[1]}')

No. of rows with age > 62: 359


working_df.Age.describe()

count    10000.000000
mean        38.921800
std         10.487806
min         18.000000
25%         32.000000
50%         37.000000
75%         44.000000
max         92.000000
Name: Age, dtype: float64


histogram_boxplot(working_df.EstimatedSalary)


px.box(working_df.EstimatedSalary,orientation='h',height=200)


working_df.EstimatedSalary.describe()

count     10000.000000
mean     100090.239881
std       57510.492818
min          11.580000
25%       51002.110000
50%      100193.915000
75%      149388.247500
max      199992.480000
Name: EstimatedSalary, dtype: float64


histogram_boxplot(working_df.Balance)


px.box(working_df.Balance, orientation='h', height=200)


#working_df[working_df.Balance == 0].count()
working_df.Balance.value_counts()

0.00         3617
105473.74       2
130170.82       2
72594.00        1
139723.90       1
             ... 
130306.49       1
92895.56        1
132005.77       1
166287.85       1
104001.38       1
Name: Balance, Length: 6382, dtype: int64


working_df.Balance.describe()

count     10000.000000
mean      76485.889288
std       62397.405202
min           0.000000
25%           0.000000
50%       97198.540000
75%      127644.240000
max      250898.090000
Name: Balance, dtype: float64


plt.figure(figsize=(20,5))
zz=sns.countplot(x=working_df.Tenure)
show_values_on_bars(zz)


plt.figure(figsize=(20,5))
zz=sns.countplot(x=working_df.NumOfProducts)
show_values_on_bars(zz)


plt.figure(figsize=(20,5))
zz=sns.countplot(x=working_df.HasCrCard)
show_values_on_bars(zz)


plt.figure(figsize=(20,5))
zz=sns.countplot(x=working_df.IsActiveMember)
show_values_on_bars(zz)


plt.figure(figsize=(20,5))
zz=sns.countplot(x=working_df.Exited)
show_values_on_bars(zz)


plt.figure(figsize=(20,5))
zz=sns.countplot(x=working_df.Geography)
show_values_on_bars(zz)


plt.figure(figsize=(20,5))
zz=sns.countplot(x=working_df.Gender)
show_values_on_bars(zz)


sns.pairplot(working_df,corner=True,diag_kind='kde')

<seaborn.axisgrid.PairGrid at 0x7fbd88a71790>


plt.figure(figsize=(15,15))
sns.heatmap(working_df.loc[:,numeric_cols].corr(), annot=True, fmt='.2f', cmap='coolwarm')

<AxesSubplot:>


working_df.groupby('Exited').mean()


working_df.groupby('Exited').median()


crosstabs = []
for i,col in enumerate(categorical_cols[1:]):
    crosstabs.append(pd.crosstab(working_df.Exited, working_df[col], normalize='columns'))
    display(crosstabs[i])


fig, axes = plt.subplots(6,1, figsize=(25,15))

for i,x in enumerate(crosstabs):
    zz=crosstabs[i].plot(kind='bar',ax=axes[i])
    show_values_on_bars(zz)


working_df[working_df.Balance==0].groupby('Exited').count().iloc[:,1]

Exited
0    3117
1     500
Name: Geography, dtype: int64


temp_df = working_df.copy()
temp_df['BalanceZero'] = temp_df.Balance.apply(lambda x: 1 if x ==0 else 0)

temp_df.groupby('BalanceZero').mean()


del(temp_df)


# Form X and y
X = working_df.drop('Exited', axis=1)
y = working_df.Exited

#Convert categorical non numeric to one hot encoding
X = pd.get_dummies(X, drop_first=True)

#Define random_state for all algorithms that use this
random_state = 314159

X


y.value_counts()

0    7963
1    2037
Name: Exited, dtype: int64


# defined class weights dictionary per keras tutorial
neg, pos = np.bincount(working_df['Exited'])
total = neg + pos
print('class weights:\n    Total: {}\n    Positive: {} ({:.2f}% of total)\n'.format(
    total, pos, 100 * pos / total))

class weights:
    Total: 10000
    Positive: 2037 (20.37% of total)


# define scaler
#https://stackoverflow.com/a/58850139 for ref on which scaler to use
scaler = RobustScaler(quantile_range=(25,75)) #using this as it retains shape of data distribution and also retains outliers 

#in any case RobustScaler yields better results than MinMax or Standard scalers


# Perform train test split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, stratify=y, random_state=random_state)


X_test


# Checking that target split ratio maintained in train and test sets
print(f'% of +ve class in target in full dataset: {working_df[working_df.Exited==1].shape[0]/ working_df.shape[0]}')
print(f'% of +ve class in target in train: {y_train.value_counts()[1]/ len(y_train):0.4f}')
print(f'% of +ve class in target in test: {y_test.value_counts()[1]/ len(y_test):0.4f}')

% of +ve class in target in full dataset: 0.2037
% of +ve class in target in train: 0.2037
% of +ve class in target in test: 0.2037


# Scaling data
# To prevent test data leaking into train, we fit the scaler on train and then transform both train and test on that scaler

X_train = pd.DataFrame(scaler.fit_transform(X_train), columns=X_train.columns)
X_test = pd.DataFrame(scaler.transform(X_test), columns = X_test.columns)



print('Scaled X_train:')
display(X_train.describe().T)

print('\nScaled X_test:')
display(X_test.describe().T)

Scaled X_train:

Scaled X_test:


# Defining metrics - keras tutorial
# I retain these functions here to aid ready reference as needed to tune models
# Modified from source found at: https://www.tensorflow.org/tutorials/structured_data/imbalanced_data

colors = plt.rcParams['axes.prop_cycle'].by_key()['color']

THRESHOLD = 0.5 # threshold used to determine if output is 0 or 1 (since sigmoid outputs a continuous no between 0 and 1)

EPOCHS=100 # baseline epochs for model run

BATCH_SIZE=100 # baseline batchsize

#metrics for model to compute
METRICS = [
      keras.metrics.TruePositives(name='tp'),
      keras.metrics.FalsePositives(name='fp'),
      keras.metrics.TrueNegatives(name='tn'),
      keras.metrics.FalseNegatives(name='fn'), 
      keras.metrics.BinaryAccuracy(name='accuracy'),
      keras.metrics.Precision(name='precision'),
      keras.metrics.Recall(name='recall'),
      keras.metrics.AUC(name='auc'),
      keras.metrics.AUC(name='prc', curve='PR'), # precision-recall curve
]

#function to define and compile model
def make_model(metrics=METRICS, output_bias=None, dropout=False, learning_rate=1e-3, activation='relu'):
    if output_bias is not None:
        print('bias being set')
        output_bias = tf.keras.initializers.Constant(output_bias)
    
    model = keras.Sequential()
  
    model.add(keras.layers.Dense(16, activation=activation,input_shape=(X_train.shape[-1],)))
    
    if dropout==True:
        model.add(keras.layers.Dropout(0.5))
    
    model.add(keras.layers.Dense(1, activation='sigmoid', bias_initializer=output_bias))

    model.compile(
        optimizer=keras.optimizers.Adam(learning_rate=learning_rate),
        loss=keras.losses.BinaryCrossentropy(),
        metrics=metrics)

    return model

#variant of above
def make_model2(metrics=METRICS, output_bias=None, dropout=False, learning_rate=1e-3):
    if output_bias is not None:
        print('bias being set')
        output_bias = tf.keras.initializers.Constant(output_bias)
    
    model = keras.Sequential()
  
    model.add(keras.layers.Dense(64, activation='relu',input_shape=(X_train.shape[-1],)))
    
    if dropout==True:
        model.add(keras.layers.Dropout(0.7))
    
    model.add(keras.layers.Dense(16, activation='relu', bias_initializer=output_bias))
    
    if dropout==True:
        model.add(keras.layers.Dropout(0.6))

    
    model.add(keras.layers.Dense(1, activation='sigmoid', bias_initializer=output_bias))

    model.compile(
        optimizer=keras.optimizers.Adam(learning_rate=learning_rate),
        loss=keras.losses.BinaryCrossentropy(),
        metrics=metrics)

    return model

#function to plot model metrics (loss, accuracy, recall and precision)
def plot_metrics(history):
  metrics = ['loss', 'accuracy', 'precision', 'recall']
  for n, metric in enumerate(metrics):
    name = metric.replace("_"," ").capitalize()
    plt.subplot(2,2,n+1)
    plt.plot(history.epoch, history.history[metric], color=colors[0], label='Train')
    plt.plot(history.epoch, history.history['val_'+metric],
             color=colors[1], linestyle="--", label='Val')
    plt.xlabel('Epoch')
    plt.ylabel(name)
    if metric == 'loss':
      plt.ylim([0, plt.ylim()[1]])
    elif metric == 'auc':
      plt.ylim([0.8,1])
    else:
      plt.ylim([0,1])

    plt.legend()


%%time
model1 = make_model()
#start with 100 epochs
history1 = model1.fit(X_train, y_train, epochs=EPOCHS, batch_size=BATCH_SIZE, use_multiprocessing=True, validation_split=0.2)

Epoch 1/100
56/56 [==============================] - 3s 20ms/step - loss: 0.5511 - tp: 0.0000e+00 - fp: 0.0000e+00 - tn: 2317.8246 - fn: 580.4211 - accuracy: 0.8023 - precision: 0.0000e+00 - recall: 0.0000e+00 - auc: 0.3840 - prc: 0.1700 - val_loss: 0.5595 - val_tp: 0.0000e+00 - val_fp: 0.0000e+00 - val_tn: 1083.0000 - val_fn: 317.0000 - val_accuracy: 0.7736 - val_precision: 0.0000e+00 - val_recall: 0.0000e+00 - val_auc: 0.5024 - val_prc: 0.2446
Epoch 2/100
56/56 [==============================] - 0s 2ms/step - loss: 0.4882 - tp: 0.0000e+00 - fp: 0.0000e+00 - tn: 2331.8772 - fn: 566.3684 - accuracy: 0.8069 - precision: 0.0000e+00 - recall: 0.0000e+00 - auc: 0.5725 - prc: 0.2741 - val_loss: 0.5201 - val_tp: 0.0000e+00 - val_fp: 0.0000e+00 - val_tn: 1083.0000 - val_fn: 317.0000 - val_accuracy: 0.7736 - val_precision: 0.0000e+00 - val_recall: 0.0000e+00 - val_auc: 0.6529 - val_prc: 0.3304
Epoch 3/100
56/56 [==============================] - 0s 2ms/step - loss: 0.4612 - tp: 0.8772 - fp: 0.1404 - tn: 2325.8947 - fn: 571.3333 - accuracy: 0.8057 - precision: 0.4561 - recall: 0.0010 - auc: 0.6985 - prc: 0.3542 - val_loss: 0.4966 - val_tp: 0.0000e+00 - val_fp: 0.0000e+00 - val_tn: 1083.0000 - val_fn: 317.0000 - val_accuracy: 0.7736 - val_precision: 0.0000e+00 - val_recall: 0.0000e+00 - val_auc: 0.7117 - val_prc: 0.3812
Epoch 4/100
56/56 [==============================] - 0s 2ms/step - loss: 0.4487 - tp: 4.4211 - fp: 3.6667 - tn: 2316.9474 - fn: 573.2105 - accuracy: 0.7994 - precision: 0.5072 - recall: 0.0067 - auc: 0.7517 - prc: 0.4158 - val_loss: 0.4837 - val_tp: 6.0000 - val_fp: 9.0000 - val_tn: 1074.0000 - val_fn: 311.0000 - val_accuracy: 0.7714 - val_precision: 0.4000 - val_recall: 0.0189 - val_auc: 0.7326 - val_prc: 0.4011
Epoch 5/100
56/56 [==============================] - 0s 2ms/step - loss: 0.4330 - tp: 19.2632 - fp: 14.2632 - tn: 2309.9649 - fn: 554.7544 - accuracy: 0.8077 - precision: 0.5500 - recall: 0.0263 - auc: 0.7570 - prc: 0.4114 - val_loss: 0.4764 - val_tp: 15.0000 - val_fp: 20.0000 - val_tn: 1063.0000 - val_fn: 302.0000 - val_accuracy: 0.7700 - val_precision: 0.4286 - val_recall: 0.0473 - val_auc: 0.7408 - val_prc: 0.4129
Epoch 6/100
56/56 [==============================] - 0s 2ms/step - loss: 0.4295 - tp: 46.8246 - fp: 28.0351 - tn: 2287.5614 - fn: 535.8246 - accuracy: 0.8021 - precision: 0.6300 - recall: 0.0733 - auc: 0.7794 - prc: 0.4674 - val_loss: 0.4709 - val_tp: 24.0000 - val_fp: 28.0000 - val_tn: 1055.0000 - val_fn: 293.0000 - val_accuracy: 0.7707 - val_precision: 0.4615 - val_recall: 0.0757 - val_auc: 0.7479 - val_prc: 0.4271
Epoch 7/100
56/56 [==============================] - 0s 2ms/step - loss: 0.4223 - tp: 58.7719 - fp: 36.2281 - tn: 2285.9649 - fn: 517.2807 - accuracy: 0.8136 - precision: 0.6416 - recall: 0.1093 - auc: 0.7688 - prc: 0.4643 - val_loss: 0.4670 - val_tp: 34.0000 - val_fp: 30.0000 - val_tn: 1053.0000 - val_fn: 283.0000 - val_accuracy: 0.7764 - val_precision: 0.5312 - val_recall: 0.1073 - val_auc: 0.7528 - val_prc: 0.4410
Epoch 8/100
56/56 [==============================] - 0s 2ms/step - loss: 0.4142 - tp: 80.1754 - fp: 51.4737 - tn: 2273.7895 - fn: 492.8070 - accuracy: 0.8126 - precision: 0.6160 - recall: 0.1389 - auc: 0.7848 - prc: 0.4915 - val_loss: 0.4622 - val_tp: 53.0000 - val_fp: 36.0000 - val_tn: 1047.0000 - val_fn: 264.0000 - val_accuracy: 0.7857 - val_precision: 0.5955 - val_recall: 0.1672 - val_auc: 0.7584 - val_prc: 0.4602
Epoch 9/100
56/56 [==============================] - 0s 2ms/step - loss: 0.4238 - tp: 101.3333 - fp: 49.0526 - tn: 2279.0351 - fn: 468.8246 - accuracy: 0.8204 - precision: 0.6793 - recall: 0.1709 - auc: 0.7593 - prc: 0.4728 - val_loss: 0.4575 - val_tp: 60.0000 - val_fp: 40.0000 - val_tn: 1043.0000 - val_fn: 257.0000 - val_accuracy: 0.7879 - val_precision: 0.6000 - val_recall: 0.1893 - val_auc: 0.7643 - val_prc: 0.4803
Epoch 10/100
56/56 [==============================] - 0s 2ms/step - loss: 0.4115 - tp: 127.1053 - fp: 59.4912 - tn: 2258.4211 - fn: 453.2281 - accuracy: 0.8227 - precision: 0.6788 - recall: 0.2182 - auc: 0.7905 - prc: 0.5199 - val_loss: 0.4541 - val_tp: 59.0000 - val_fp: 36.0000 - val_tn: 1047.0000 - val_fn: 258.0000 - val_accuracy: 0.7900 - val_precision: 0.6211 - val_recall: 0.1861 - val_auc: 0.7686 - val_prc: 0.4982
Epoch 11/100
56/56 [==============================] - 0s 2ms/step - loss: 0.4123 - tp: 142.0526 - fp: 59.1930 - tn: 2251.0702 - fn: 445.9298 - accuracy: 0.8231 - precision: 0.6908 - recall: 0.2309 - auc: 0.7904 - prc: 0.5287 - val_loss: 0.4501 - val_tp: 65.0000 - val_fp: 32.0000 - val_tn: 1051.0000 - val_fn: 252.0000 - val_accuracy: 0.7971 - val_precision: 0.6701 - val_recall: 0.2050 - val_auc: 0.7735 - val_prc: 0.5136
Epoch 12/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3914 - tp: 134.8947 - fp: 48.8947 - tn: 2287.7018 - fn: 426.7544 - accuracy: 0.8388 - precision: 0.7402 - recall: 0.2387 - auc: 0.8001 - prc: 0.5427 - val_loss: 0.4444 - val_tp: 79.0000 - val_fp: 42.0000 - val_tn: 1041.0000 - val_fn: 238.0000 - val_accuracy: 0.8000 - val_precision: 0.6529 - val_recall: 0.2492 - val_auc: 0.7796 - val_prc: 0.5267
Epoch 13/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3942 - tp: 155.3860 - fp: 61.9649 - tn: 2272.0877 - fn: 408.8070 - accuracy: 0.8362 - precision: 0.6989 - recall: 0.2787 - auc: 0.7988 - prc: 0.5534 - val_loss: 0.4401 - val_tp: 80.0000 - val_fp: 40.0000 - val_tn: 1043.0000 - val_fn: 237.0000 - val_accuracy: 0.8021 - val_precision: 0.6667 - val_recall: 0.2524 - val_auc: 0.7853 - val_prc: 0.5393
Epoch 14/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3963 - tp: 176.6491 - fp: 69.1053 - tn: 2249.2281 - fn: 403.2632 - accuracy: 0.8334 - precision: 0.7146 - recall: 0.3023 - auc: 0.8094 - prc: 0.5775 - val_loss: 0.4373 - val_tp: 81.0000 - val_fp: 37.0000 - val_tn: 1046.0000 - val_fn: 236.0000 - val_accuracy: 0.8050 - val_precision: 0.6864 - val_recall: 0.2555 - val_auc: 0.7893 - val_prc: 0.5506
Epoch 15/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3929 - tp: 175.1579 - fp: 63.5263 - tn: 2255.8947 - fn: 403.6667 - accuracy: 0.8376 - precision: 0.7364 - recall: 0.2912 - auc: 0.8050 - prc: 0.5816 - val_loss: 0.4338 - val_tp: 88.0000 - val_fp: 39.0000 - val_tn: 1044.0000 - val_fn: 229.0000 - val_accuracy: 0.8086 - val_precision: 0.6929 - val_recall: 0.2776 - val_auc: 0.7938 - val_prc: 0.5584
Epoch 16/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3951 - tp: 184.9123 - fp: 65.2281 - tn: 2250.4386 - fn: 397.6667 - accuracy: 0.8379 - precision: 0.7304 - recall: 0.3083 - auc: 0.8049 - prc: 0.5815 - val_loss: 0.4302 - val_tp: 91.0000 - val_fp: 40.0000 - val_tn: 1043.0000 - val_fn: 226.0000 - val_accuracy: 0.8100 - val_precision: 0.6947 - val_recall: 0.2871 - val_auc: 0.7982 - val_prc: 0.5697
Epoch 17/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3853 - tp: 185.3158 - fp: 59.6140 - tn: 2261.4737 - fn: 391.8421 - accuracy: 0.8432 - precision: 0.7610 - recall: 0.3094 - auc: 0.8129 - prc: 0.5944 - val_loss: 0.4283 - val_tp: 89.0000 - val_fp: 38.0000 - val_tn: 1045.0000 - val_fn: 228.0000 - val_accuracy: 0.8100 - val_precision: 0.7008 - val_recall: 0.2808 - val_auc: 0.8015 - val_prc: 0.5763
Epoch 18/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3786 - tp: 190.1404 - fp: 61.9298 - tn: 2263.3509 - fn: 382.8246 - accuracy: 0.8465 - precision: 0.7643 - recall: 0.3303 - auc: 0.8232 - prc: 0.6077 - val_loss: 0.4240 - val_tp: 100.0000 - val_fp: 42.0000 - val_tn: 1041.0000 - val_fn: 217.0000 - val_accuracy: 0.8150 - val_precision: 0.7042 - val_recall: 0.3155 - val_auc: 0.8046 - val_prc: 0.5843
Epoch 19/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3790 - tp: 196.4561 - fp: 69.8246 - tn: 2263.5965 - fn: 368.3684 - accuracy: 0.8462 - precision: 0.7235 - recall: 0.3505 - auc: 0.8182 - prc: 0.5886 - val_loss: 0.4212 - val_tp: 103.0000 - val_fp: 43.0000 - val_tn: 1040.0000 - val_fn: 214.0000 - val_accuracy: 0.8164 - val_precision: 0.7055 - val_recall: 0.3249 - val_auc: 0.8080 - val_prc: 0.5878
Epoch 20/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3835 - tp: 203.8772 - fp: 74.8421 - tn: 2251.2807 - fn: 368.2456 - accuracy: 0.8415 - precision: 0.7065 - recall: 0.3446 - auc: 0.8196 - prc: 0.5731 - val_loss: 0.4193 - val_tp: 102.0000 - val_fp: 43.0000 - val_tn: 1040.0000 - val_fn: 215.0000 - val_accuracy: 0.8157 - val_precision: 0.7034 - val_recall: 0.3218 - val_auc: 0.8109 - val_prc: 0.5940
Epoch 21/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3752 - tp: 225.4561 - fp: 76.3158 - tn: 2226.9649 - fn: 369.5088 - accuracy: 0.8430 - precision: 0.7486 - recall: 0.3727 - auc: 0.8387 - prc: 0.6366 - val_loss: 0.4194 - val_tp: 97.0000 - val_fp: 37.0000 - val_tn: 1046.0000 - val_fn: 220.0000 - val_accuracy: 0.8164 - val_precision: 0.7239 - val_recall: 0.3060 - val_auc: 0.8133 - val_prc: 0.5990
Epoch 22/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3599 - tp: 199.4211 - fp: 62.4386 - tn: 2275.3860 - fn: 361.0000 - accuracy: 0.8560 - precision: 0.7656 - recall: 0.3692 - auc: 0.8360 - prc: 0.6309 - val_loss: 0.4135 - val_tp: 111.0000 - val_fp: 47.0000 - val_tn: 1036.0000 - val_fn: 206.0000 - val_accuracy: 0.8193 - val_precision: 0.7025 - val_recall: 0.3502 - val_auc: 0.8157 - val_prc: 0.6052
Epoch 23/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3633 - tp: 211.5965 - fp: 75.7368 - tn: 2266.2281 - fn: 344.6842 - accuracy: 0.8552 - precision: 0.7245 - recall: 0.3826 - auc: 0.8321 - prc: 0.5957 - val_loss: 0.4128 - val_tp: 103.0000 - val_fp: 43.0000 - val_tn: 1040.0000 - val_fn: 214.0000 - val_accuracy: 0.8164 - val_precision: 0.7055 - val_recall: 0.3249 - val_auc: 0.8177 - val_prc: 0.6087
Epoch 24/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3665 - tp: 226.6316 - fp: 74.5088 - tn: 2249.9474 - fn: 347.1579 - accuracy: 0.8556 - precision: 0.7510 - recall: 0.3934 - auc: 0.8287 - prc: 0.6214 - val_loss: 0.4102 - val_tp: 108.0000 - val_fp: 44.0000 - val_tn: 1039.0000 - val_fn: 209.0000 - val_accuracy: 0.8193 - val_precision: 0.7105 - val_recall: 0.3407 - val_auc: 0.8197 - val_prc: 0.6123
Epoch 25/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3652 - tp: 222.2982 - fp: 74.6491 - tn: 2248.9123 - fn: 352.3860 - accuracy: 0.8519 - precision: 0.7453 - recall: 0.3865 - auc: 0.8343 - prc: 0.6276 - val_loss: 0.4094 - val_tp: 107.0000 - val_fp: 41.0000 - val_tn: 1042.0000 - val_fn: 210.0000 - val_accuracy: 0.8207 - val_precision: 0.7230 - val_recall: 0.3375 - val_auc: 0.8221 - val_prc: 0.6160
Epoch 26/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3551 - tp: 226.2105 - fp: 69.0702 - tn: 2253.0351 - fn: 349.9298 - accuracy: 0.8595 - precision: 0.7722 - recall: 0.3982 - auc: 0.8410 - prc: 0.6473 - val_loss: 0.4076 - val_tp: 109.0000 - val_fp: 41.0000 - val_tn: 1042.0000 - val_fn: 208.0000 - val_accuracy: 0.8221 - val_precision: 0.7267 - val_recall: 0.3438 - val_auc: 0.8228 - val_prc: 0.6190
Epoch 27/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3590 - tp: 212.6842 - fp: 64.8246 - tn: 2264.5439 - fn: 356.1930 - accuracy: 0.8542 - precision: 0.7611 - recall: 0.3654 - auc: 0.8372 - prc: 0.6332 - val_loss: 0.4055 - val_tp: 113.0000 - val_fp: 43.0000 - val_tn: 1040.0000 - val_fn: 204.0000 - val_accuracy: 0.8236 - val_precision: 0.7244 - val_recall: 0.3565 - val_auc: 0.8247 - val_prc: 0.6220
Epoch 28/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3511 - tp: 202.7895 - fp: 69.8421 - tn: 2277.7368 - fn: 347.8772 - accuracy: 0.8599 - precision: 0.7386 - recall: 0.3791 - auc: 0.8392 - prc: 0.6084 - val_loss: 0.4036 - val_tp: 120.0000 - val_fp: 47.0000 - val_tn: 1036.0000 - val_fn: 197.0000 - val_accuracy: 0.8257 - val_precision: 0.7186 - val_recall: 0.3785 - val_auc: 0.8253 - val_prc: 0.6253
Epoch 29/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3568 - tp: 234.5088 - fp: 76.7018 - tn: 2252.9825 - fn: 334.0526 - accuracy: 0.8601 - precision: 0.7571 - recall: 0.4147 - auc: 0.8388 - prc: 0.6432 - val_loss: 0.4029 - val_tp: 115.0000 - val_fp: 44.0000 - val_tn: 1039.0000 - val_fn: 202.0000 - val_accuracy: 0.8243 - val_precision: 0.7233 - val_recall: 0.3628 - val_auc: 0.8268 - val_prc: 0.6283
Epoch 30/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3454 - tp: 229.2632 - fp: 72.7368 - tn: 2251.3509 - fn: 344.8947 - accuracy: 0.8542 - precision: 0.7593 - recall: 0.3955 - auc: 0.8628 - prc: 0.6649 - val_loss: 0.4016 - val_tp: 117.0000 - val_fp: 42.0000 - val_tn: 1041.0000 - val_fn: 200.0000 - val_accuracy: 0.8271 - val_precision: 0.7358 - val_recall: 0.3691 - val_auc: 0.8281 - val_prc: 0.6314
Epoch 31/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3497 - tp: 246.8947 - fp: 66.5439 - tn: 2247.9649 - fn: 336.8421 - accuracy: 0.8625 - precision: 0.7977 - recall: 0.4288 - auc: 0.8547 - prc: 0.6742 - val_loss: 0.4009 - val_tp: 118.0000 - val_fp: 39.0000 - val_tn: 1044.0000 - val_fn: 199.0000 - val_accuracy: 0.8300 - val_precision: 0.7516 - val_recall: 0.3722 - val_auc: 0.8293 - val_prc: 0.6343
Epoch 32/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3528 - tp: 238.4035 - fp: 73.9123 - tn: 2250.7719 - fn: 335.1579 - accuracy: 0.8580 - precision: 0.7595 - recall: 0.4144 - auc: 0.8475 - prc: 0.6514 - val_loss: 0.3994 - val_tp: 125.0000 - val_fp: 46.0000 - val_tn: 1037.0000 - val_fn: 192.0000 - val_accuracy: 0.8300 - val_precision: 0.7310 - val_recall: 0.3943 - val_auc: 0.8293 - val_prc: 0.6341
Epoch 33/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3550 - tp: 245.2105 - fp: 79.0175 - tn: 2240.9649 - fn: 333.0526 - accuracy: 0.8561 - precision: 0.7519 - recall: 0.4154 - auc: 0.8465 - prc: 0.6522 - val_loss: 0.3986 - val_tp: 120.0000 - val_fp: 40.0000 - val_tn: 1043.0000 - val_fn: 197.0000 - val_accuracy: 0.8307 - val_precision: 0.7500 - val_recall: 0.3785 - val_auc: 0.8309 - val_prc: 0.6392
Epoch 34/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3429 - tp: 243.7544 - fp: 72.0000 - tn: 2247.0351 - fn: 335.4561 - accuracy: 0.8609 - precision: 0.7899 - recall: 0.4183 - auc: 0.8613 - prc: 0.6801 - val_loss: 0.3982 - val_tp: 122.0000 - val_fp: 40.0000 - val_tn: 1043.0000 - val_fn: 195.0000 - val_accuracy: 0.8321 - val_precision: 0.7531 - val_recall: 0.3849 - val_auc: 0.8314 - val_prc: 0.6414
Epoch 35/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3528 - tp: 238.5439 - fp: 70.0351 - tn: 2245.0526 - fn: 344.6140 - accuracy: 0.8571 - precision: 0.7776 - recall: 0.4093 - auc: 0.8512 - prc: 0.6643 - val_loss: 0.3971 - val_tp: 123.0000 - val_fp: 40.0000 - val_tn: 1043.0000 - val_fn: 194.0000 - val_accuracy: 0.8329 - val_precision: 0.7546 - val_recall: 0.3880 - val_auc: 0.8326 - val_prc: 0.6420
Epoch 36/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3439 - tp: 236.5439 - fp: 69.9123 - tn: 2269.7895 - fn: 322.0000 - accuracy: 0.8635 - precision: 0.7855 - recall: 0.4158 - auc: 0.8548 - prc: 0.6648 - val_loss: 0.3946 - val_tp: 133.0000 - val_fp: 48.0000 - val_tn: 1035.0000 - val_fn: 184.0000 - val_accuracy: 0.8343 - val_precision: 0.7348 - val_recall: 0.4196 - val_auc: 0.8325 - val_prc: 0.6447
Epoch 37/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3376 - tp: 263.2807 - fp: 81.9298 - tn: 2236.2982 - fn: 316.7368 - accuracy: 0.8661 - precision: 0.7711 - recall: 0.4574 - auc: 0.8608 - prc: 0.6861 - val_loss: 0.3956 - val_tp: 127.0000 - val_fp: 39.0000 - val_tn: 1044.0000 - val_fn: 190.0000 - val_accuracy: 0.8364 - val_precision: 0.7651 - val_recall: 0.4006 - val_auc: 0.8333 - val_prc: 0.6465
Epoch 38/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3446 - tp: 262.7018 - fp: 70.5789 - tn: 2238.4386 - fn: 326.5263 - accuracy: 0.8653 - precision: 0.8048 - recall: 0.4436 - auc: 0.8575 - prc: 0.6842 - val_loss: 0.3963 - val_tp: 121.0000 - val_fp: 39.0000 - val_tn: 1044.0000 - val_fn: 196.0000 - val_accuracy: 0.8321 - val_precision: 0.7563 - val_recall: 0.3817 - val_auc: 0.8342 - val_prc: 0.6465
Epoch 39/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3364 - tp: 231.1579 - fp: 60.1053 - tn: 2274.8421 - fn: 332.1404 - accuracy: 0.8656 - precision: 0.7830 - recall: 0.4013 - auc: 0.8523 - prc: 0.6680 - val_loss: 0.3927 - val_tp: 134.0000 - val_fp: 49.0000 - val_tn: 1034.0000 - val_fn: 183.0000 - val_accuracy: 0.8343 - val_precision: 0.7322 - val_recall: 0.4227 - val_auc: 0.8343 - val_prc: 0.6456
Epoch 40/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3375 - tp: 251.1228 - fp: 76.3333 - tn: 2252.7719 - fn: 318.0175 - accuracy: 0.8641 - precision: 0.7627 - recall: 0.4449 - auc: 0.8617 - prc: 0.6768 - val_loss: 0.3919 - val_tp: 135.0000 - val_fp: 46.0000 - val_tn: 1037.0000 - val_fn: 182.0000 - val_accuracy: 0.8371 - val_precision: 0.7459 - val_recall: 0.4259 - val_auc: 0.8355 - val_prc: 0.6493
Epoch 41/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3542 - tp: 250.8421 - fp: 79.0877 - tn: 2236.9298 - fn: 331.3860 - accuracy: 0.8521 - precision: 0.7546 - recall: 0.4185 - auc: 0.8551 - prc: 0.6652 - val_loss: 0.3939 - val_tp: 126.0000 - val_fp: 39.0000 - val_tn: 1044.0000 - val_fn: 191.0000 - val_accuracy: 0.8357 - val_precision: 0.7636 - val_recall: 0.3975 - val_auc: 0.8353 - val_prc: 0.6498
Epoch 42/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3382 - tp: 251.1053 - fp: 76.0702 - tn: 2242.3860 - fn: 328.6842 - accuracy: 0.8608 - precision: 0.7746 - recall: 0.4255 - auc: 0.8653 - prc: 0.6805 - val_loss: 0.3927 - val_tp: 132.0000 - val_fp: 39.0000 - val_tn: 1044.0000 - val_fn: 185.0000 - val_accuracy: 0.8400 - val_precision: 0.7719 - val_recall: 0.4164 - val_auc: 0.8359 - val_prc: 0.6510
Epoch 43/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3378 - tp: 245.2105 - fp: 66.6140 - tn: 2264.8596 - fn: 321.5614 - accuracy: 0.8645 - precision: 0.7948 - recall: 0.4310 - auc: 0.8645 - prc: 0.6812 - val_loss: 0.3909 - val_tp: 134.0000 - val_fp: 46.0000 - val_tn: 1037.0000 - val_fn: 183.0000 - val_accuracy: 0.8364 - val_precision: 0.7444 - val_recall: 0.4227 - val_auc: 0.8357 - val_prc: 0.6518
Epoch 44/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3411 - tp: 248.6316 - fp: 83.4035 - tn: 2240.2982 - fn: 325.9123 - accuracy: 0.8599 - precision: 0.7430 - recall: 0.4339 - auc: 0.8576 - prc: 0.6665 - val_loss: 0.3906 - val_tp: 133.0000 - val_fp: 44.0000 - val_tn: 1039.0000 - val_fn: 184.0000 - val_accuracy: 0.8371 - val_precision: 0.7514 - val_recall: 0.4196 - val_auc: 0.8361 - val_prc: 0.6535
Epoch 45/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3418 - tp: 252.5614 - fp: 76.5263 - tn: 2240.7368 - fn: 328.4211 - accuracy: 0.8626 - precision: 0.7806 - recall: 0.4364 - auc: 0.8577 - prc: 0.6822 - val_loss: 0.3918 - val_tp: 129.0000 - val_fp: 41.0000 - val_tn: 1042.0000 - val_fn: 188.0000 - val_accuracy: 0.8364 - val_precision: 0.7588 - val_recall: 0.4069 - val_auc: 0.8366 - val_prc: 0.6546
Epoch 46/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3340 - tp: 242.7719 - fp: 70.7193 - tn: 2256.0351 - fn: 328.7193 - accuracy: 0.8633 - precision: 0.7689 - recall: 0.4292 - auc: 0.8616 - prc: 0.6853 - val_loss: 0.3897 - val_tp: 134.0000 - val_fp: 47.0000 - val_tn: 1036.0000 - val_fn: 183.0000 - val_accuracy: 0.8357 - val_precision: 0.7403 - val_recall: 0.4227 - val_auc: 0.8373 - val_prc: 0.6543
Epoch 47/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3418 - tp: 256.2456 - fp: 76.8421 - tn: 2237.2281 - fn: 327.9298 - accuracy: 0.8593 - precision: 0.7792 - recall: 0.4272 - auc: 0.8612 - prc: 0.6932 - val_loss: 0.3915 - val_tp: 128.0000 - val_fp: 40.0000 - val_tn: 1043.0000 - val_fn: 189.0000 - val_accuracy: 0.8364 - val_precision: 0.7619 - val_recall: 0.4038 - val_auc: 0.8376 - val_prc: 0.6572
Epoch 48/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3275 - tp: 242.9474 - fp: 65.5088 - tn: 2274.7193 - fn: 315.0702 - accuracy: 0.8713 - precision: 0.7895 - recall: 0.4322 - auc: 0.8611 - prc: 0.6834 - val_loss: 0.3890 - val_tp: 135.0000 - val_fp: 47.0000 - val_tn: 1036.0000 - val_fn: 182.0000 - val_accuracy: 0.8364 - val_precision: 0.7418 - val_recall: 0.4259 - val_auc: 0.8376 - val_prc: 0.6560
Epoch 49/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3331 - tp: 259.7895 - fp: 85.1053 - tn: 2249.4211 - fn: 303.9298 - accuracy: 0.8668 - precision: 0.7525 - recall: 0.4741 - auc: 0.8605 - prc: 0.6914 - val_loss: 0.3875 - val_tp: 141.0000 - val_fp: 49.0000 - val_tn: 1034.0000 - val_fn: 176.0000 - val_accuracy: 0.8393 - val_precision: 0.7421 - val_recall: 0.4448 - val_auc: 0.8379 - val_prc: 0.6580
Epoch 50/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3517 - tp: 252.3158 - fp: 93.2807 - tn: 2236.1579 - fn: 316.4912 - accuracy: 0.8524 - precision: 0.7091 - recall: 0.4360 - auc: 0.8472 - prc: 0.6505 - val_loss: 0.3883 - val_tp: 133.0000 - val_fp: 43.0000 - val_tn: 1040.0000 - val_fn: 184.0000 - val_accuracy: 0.8379 - val_precision: 0.7557 - val_recall: 0.4196 - val_auc: 0.8386 - val_prc: 0.6598
Epoch 51/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3302 - tp: 255.0526 - fp: 82.9825 - tn: 2246.0175 - fn: 314.1930 - accuracy: 0.8657 - precision: 0.7572 - recall: 0.4649 - auc: 0.8653 - prc: 0.6937 - val_loss: 0.3886 - val_tp: 133.0000 - val_fp: 43.0000 - val_tn: 1040.0000 - val_fn: 184.0000 - val_accuracy: 0.8379 - val_precision: 0.7557 - val_recall: 0.4196 - val_auc: 0.8387 - val_prc: 0.6593
Epoch 52/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3465 - tp: 243.2281 - fp: 77.2105 - tn: 2250.4035 - fn: 327.4035 - accuracy: 0.8562 - precision: 0.7508 - recall: 0.4080 - auc: 0.8525 - prc: 0.6596 - val_loss: 0.3888 - val_tp: 133.0000 - val_fp: 43.0000 - val_tn: 1040.0000 - val_fn: 184.0000 - val_accuracy: 0.8379 - val_precision: 0.7557 - val_recall: 0.4196 - val_auc: 0.8391 - val_prc: 0.6594
Epoch 53/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3364 - tp: 258.6316 - fp: 77.9825 - tn: 2247.5789 - fn: 314.0526 - accuracy: 0.8666 - precision: 0.7691 - recall: 0.4603 - auc: 0.8584 - prc: 0.6883 - val_loss: 0.3881 - val_tp: 137.0000 - val_fp: 44.0000 - val_tn: 1039.0000 - val_fn: 180.0000 - val_accuracy: 0.8400 - val_precision: 0.7569 - val_recall: 0.4322 - val_auc: 0.8389 - val_prc: 0.6610
Epoch 54/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3251 - tp: 252.1930 - fp: 79.0526 - tn: 2253.9123 - fn: 313.0877 - accuracy: 0.8677 - precision: 0.7665 - recall: 0.4483 - auc: 0.8659 - prc: 0.6938 - val_loss: 0.3885 - val_tp: 134.0000 - val_fp: 40.0000 - val_tn: 1043.0000 - val_fn: 183.0000 - val_accuracy: 0.8407 - val_precision: 0.7701 - val_recall: 0.4227 - val_auc: 0.8388 - val_prc: 0.6627
Epoch 55/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3342 - tp: 253.2632 - fp: 78.6491 - tn: 2250.1930 - fn: 316.1404 - accuracy: 0.8642 - precision: 0.7695 - recall: 0.4423 - auc: 0.8621 - prc: 0.6796 - val_loss: 0.3874 - val_tp: 137.0000 - val_fp: 45.0000 - val_tn: 1038.0000 - val_fn: 180.0000 - val_accuracy: 0.8393 - val_precision: 0.7527 - val_recall: 0.4322 - val_auc: 0.8397 - val_prc: 0.6610
Epoch 56/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3306 - tp: 269.4035 - fp: 76.9123 - tn: 2241.9123 - fn: 310.0175 - accuracy: 0.8676 - precision: 0.7888 - recall: 0.4696 - auc: 0.8688 - prc: 0.7069 - val_loss: 0.3876 - val_tp: 138.0000 - val_fp: 44.0000 - val_tn: 1039.0000 - val_fn: 179.0000 - val_accuracy: 0.8407 - val_precision: 0.7582 - val_recall: 0.4353 - val_auc: 0.8397 - val_prc: 0.6609
Epoch 57/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3254 - tp: 254.9649 - fp: 76.0000 - tn: 2249.7895 - fn: 317.4912 - accuracy: 0.8663 - precision: 0.7761 - recall: 0.4495 - auc: 0.8698 - prc: 0.7031 - val_loss: 0.3860 - val_tp: 139.0000 - val_fp: 47.0000 - val_tn: 1036.0000 - val_fn: 178.0000 - val_accuracy: 0.8393 - val_precision: 0.7473 - val_recall: 0.4385 - val_auc: 0.8398 - val_prc: 0.6625
Epoch 58/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3371 - tp: 254.2456 - fp: 76.2807 - tn: 2244.1579 - fn: 323.5614 - accuracy: 0.8638 - precision: 0.7702 - recall: 0.4396 - auc: 0.8607 - prc: 0.6797 - val_loss: 0.3877 - val_tp: 135.0000 - val_fp: 38.0000 - val_tn: 1045.0000 - val_fn: 182.0000 - val_accuracy: 0.8429 - val_precision: 0.7803 - val_recall: 0.4259 - val_auc: 0.8394 - val_prc: 0.6633
Epoch 59/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3390 - tp: 254.2807 - fp: 72.5965 - tn: 2250.2456 - fn: 321.1228 - accuracy: 0.8618 - precision: 0.7813 - recall: 0.4412 - auc: 0.8628 - prc: 0.6936 - val_loss: 0.3862 - val_tp: 138.0000 - val_fp: 47.0000 - val_tn: 1036.0000 - val_fn: 179.0000 - val_accuracy: 0.8386 - val_precision: 0.7459 - val_recall: 0.4353 - val_auc: 0.8399 - val_prc: 0.6638
Epoch 60/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3379 - tp: 250.9123 - fp: 79.3860 - tn: 2246.4211 - fn: 321.5263 - accuracy: 0.8620 - precision: 0.7583 - recall: 0.4360 - auc: 0.8585 - prc: 0.6762 - val_loss: 0.3863 - val_tp: 139.0000 - val_fp: 46.0000 - val_tn: 1037.0000 - val_fn: 178.0000 - val_accuracy: 0.8400 - val_precision: 0.7514 - val_recall: 0.4385 - val_auc: 0.8401 - val_prc: 0.6639
Epoch 61/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3307 - tp: 273.6491 - fp: 76.3509 - tn: 2236.7544 - fn: 311.4912 - accuracy: 0.8685 - precision: 0.7932 - recall: 0.4739 - auc: 0.8702 - prc: 0.7045 - val_loss: 0.3876 - val_tp: 136.0000 - val_fp: 37.0000 - val_tn: 1046.0000 - val_fn: 181.0000 - val_accuracy: 0.8443 - val_precision: 0.7861 - val_recall: 0.4290 - val_auc: 0.8400 - val_prc: 0.6663
Epoch 62/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3322 - tp: 251.0702 - fp: 76.7895 - tn: 2246.4561 - fn: 323.9298 - accuracy: 0.8610 - precision: 0.7664 - recall: 0.4342 - auc: 0.8675 - prc: 0.6900 - val_loss: 0.3852 - val_tp: 139.0000 - val_fp: 46.0000 - val_tn: 1037.0000 - val_fn: 178.0000 - val_accuracy: 0.8400 - val_precision: 0.7514 - val_recall: 0.4385 - val_auc: 0.8403 - val_prc: 0.6652
Epoch 63/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3334 - tp: 260.9825 - fp: 67.1228 - tn: 2252.3333 - fn: 317.8070 - accuracy: 0.8703 - precision: 0.8071 - recall: 0.4546 - auc: 0.8621 - prc: 0.6969 - val_loss: 0.3842 - val_tp: 143.0000 - val_fp: 52.0000 - val_tn: 1031.0000 - val_fn: 174.0000 - val_accuracy: 0.8386 - val_precision: 0.7333 - val_recall: 0.4511 - val_auc: 0.8408 - val_prc: 0.6673
Epoch 64/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3436 - tp: 271.5439 - fp: 81.1228 - tn: 2234.3509 - fn: 311.2281 - accuracy: 0.8617 - precision: 0.7581 - recall: 0.4557 - auc: 0.8564 - prc: 0.6744 - val_loss: 0.3869 - val_tp: 135.0000 - val_fp: 38.0000 - val_tn: 1045.0000 - val_fn: 182.0000 - val_accuracy: 0.8429 - val_precision: 0.7803 - val_recall: 0.4259 - val_auc: 0.8410 - val_prc: 0.6675
Epoch 65/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3326 - tp: 258.8772 - fp: 75.0000 - tn: 2247.7368 - fn: 316.6316 - accuracy: 0.8629 - precision: 0.7621 - recall: 0.4518 - auc: 0.8650 - prc: 0.6954 - val_loss: 0.3849 - val_tp: 141.0000 - val_fp: 47.0000 - val_tn: 1036.0000 - val_fn: 176.0000 - val_accuracy: 0.8407 - val_precision: 0.7500 - val_recall: 0.4448 - val_auc: 0.8404 - val_prc: 0.6674
Epoch 66/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3327 - tp: 262.1754 - fp: 75.4561 - tn: 2247.9298 - fn: 312.6842 - accuracy: 0.8633 - precision: 0.7670 - recall: 0.4576 - auc: 0.8649 - prc: 0.6984 - val_loss: 0.3855 - val_tp: 138.0000 - val_fp: 44.0000 - val_tn: 1039.0000 - val_fn: 179.0000 - val_accuracy: 0.8407 - val_precision: 0.7582 - val_recall: 0.4353 - val_auc: 0.8411 - val_prc: 0.6682
Epoch 67/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3315 - tp: 258.5614 - fp: 79.9825 - tn: 2245.7544 - fn: 313.9474 - accuracy: 0.8646 - precision: 0.7679 - recall: 0.4552 - auc: 0.8642 - prc: 0.6973 - val_loss: 0.3839 - val_tp: 141.0000 - val_fp: 50.0000 - val_tn: 1033.0000 - val_fn: 176.0000 - val_accuracy: 0.8386 - val_precision: 0.7382 - val_recall: 0.4448 - val_auc: 0.8416 - val_prc: 0.6693
Epoch 68/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3392 - tp: 270.8246 - fp: 81.7368 - tn: 2238.0526 - fn: 307.6316 - accuracy: 0.8644 - precision: 0.7640 - recall: 0.4751 - auc: 0.8589 - prc: 0.6994 - val_loss: 0.3857 - val_tp: 140.0000 - val_fp: 45.0000 - val_tn: 1038.0000 - val_fn: 177.0000 - val_accuracy: 0.8414 - val_precision: 0.7568 - val_recall: 0.4416 - val_auc: 0.8412 - val_prc: 0.6676
Epoch 69/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3338 - tp: 259.8596 - fp: 79.8596 - tn: 2244.2632 - fn: 314.2632 - accuracy: 0.8603 - precision: 0.7507 - recall: 0.4457 - auc: 0.8659 - prc: 0.6863 - val_loss: 0.3835 - val_tp: 142.0000 - val_fp: 47.0000 - val_tn: 1036.0000 - val_fn: 175.0000 - val_accuracy: 0.8414 - val_precision: 0.7513 - val_recall: 0.4479 - val_auc: 0.8416 - val_prc: 0.6698
Epoch 70/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3350 - tp: 264.8772 - fp: 77.4035 - tn: 2250.0526 - fn: 305.9123 - accuracy: 0.8641 - precision: 0.7643 - recall: 0.4610 - auc: 0.8646 - prc: 0.6834 - val_loss: 0.3844 - val_tp: 139.0000 - val_fp: 44.0000 - val_tn: 1039.0000 - val_fn: 178.0000 - val_accuracy: 0.8414 - val_precision: 0.7596 - val_recall: 0.4385 - val_auc: 0.8419 - val_prc: 0.6702
Epoch 71/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3120 - tp: 273.2632 - fp: 72.7544 - tn: 2256.9649 - fn: 295.2632 - accuracy: 0.8773 - precision: 0.7941 - recall: 0.4811 - auc: 0.8791 - prc: 0.7108 - val_loss: 0.3841 - val_tp: 140.0000 - val_fp: 46.0000 - val_tn: 1037.0000 - val_fn: 177.0000 - val_accuracy: 0.8407 - val_precision: 0.7527 - val_recall: 0.4416 - val_auc: 0.8420 - val_prc: 0.6697
Epoch 72/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3337 - tp: 267.7895 - fp: 86.3158 - tn: 2231.7544 - fn: 312.3860 - accuracy: 0.8620 - precision: 0.7635 - recall: 0.4544 - auc: 0.8675 - prc: 0.6947 - val_loss: 0.3859 - val_tp: 132.0000 - val_fp: 38.0000 - val_tn: 1045.0000 - val_fn: 185.0000 - val_accuracy: 0.8407 - val_precision: 0.7765 - val_recall: 0.4164 - val_auc: 0.8412 - val_prc: 0.6718
Epoch 73/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3401 - tp: 255.1053 - fp: 79.8772 - tn: 2239.7895 - fn: 323.4737 - accuracy: 0.8593 - precision: 0.7658 - recall: 0.4393 - auc: 0.8613 - prc: 0.6860 - val_loss: 0.3846 - val_tp: 138.0000 - val_fp: 43.0000 - val_tn: 1040.0000 - val_fn: 179.0000 - val_accuracy: 0.8414 - val_precision: 0.7624 - val_recall: 0.4353 - val_auc: 0.8422 - val_prc: 0.6709
Epoch 74/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3289 - tp: 252.5965 - fp: 74.7895 - tn: 2264.8421 - fn: 306.0175 - accuracy: 0.8696 - precision: 0.7740 - recall: 0.4533 - auc: 0.8626 - prc: 0.6804 - val_loss: 0.3833 - val_tp: 140.0000 - val_fp: 47.0000 - val_tn: 1036.0000 - val_fn: 177.0000 - val_accuracy: 0.8400 - val_precision: 0.7487 - val_recall: 0.4416 - val_auc: 0.8426 - val_prc: 0.6708
Epoch 75/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3235 - tp: 264.7719 - fp: 88.4211 - tn: 2246.6316 - fn: 298.4211 - accuracy: 0.8678 - precision: 0.7508 - recall: 0.4760 - auc: 0.8673 - prc: 0.7027 - val_loss: 0.3835 - val_tp: 140.0000 - val_fp: 45.0000 - val_tn: 1038.0000 - val_fn: 177.0000 - val_accuracy: 0.8414 - val_precision: 0.7568 - val_recall: 0.4416 - val_auc: 0.8426 - val_prc: 0.6715
Epoch 76/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3340 - tp: 268.3158 - fp: 82.7544 - tn: 2238.7368 - fn: 308.4386 - accuracy: 0.8621 - precision: 0.7636 - recall: 0.4630 - auc: 0.8699 - prc: 0.6958 - val_loss: 0.3830 - val_tp: 138.0000 - val_fp: 45.0000 - val_tn: 1038.0000 - val_fn: 179.0000 - val_accuracy: 0.8400 - val_precision: 0.7541 - val_recall: 0.4353 - val_auc: 0.8430 - val_prc: 0.6729
Epoch 77/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3236 - tp: 276.9649 - fp: 77.9298 - tn: 2236.8596 - fn: 306.4912 - accuracy: 0.8681 - precision: 0.7907 - recall: 0.4821 - auc: 0.8795 - prc: 0.7205 - val_loss: 0.3845 - val_tp: 138.0000 - val_fp: 42.0000 - val_tn: 1041.0000 - val_fn: 179.0000 - val_accuracy: 0.8421 - val_precision: 0.7667 - val_recall: 0.4353 - val_auc: 0.8419 - val_prc: 0.6720
Epoch 78/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3330 - tp: 283.5965 - fp: 80.9825 - tn: 2226.9474 - fn: 306.7193 - accuracy: 0.8624 - precision: 0.7725 - recall: 0.4761 - auc: 0.8717 - prc: 0.7111 - val_loss: 0.3849 - val_tp: 133.0000 - val_fp: 40.0000 - val_tn: 1043.0000 - val_fn: 184.0000 - val_accuracy: 0.8400 - val_precision: 0.7688 - val_recall: 0.4196 - val_auc: 0.8431 - val_prc: 0.6729
Epoch 79/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3307 - tp: 242.8596 - fp: 73.6667 - tn: 2264.2982 - fn: 317.4211 - accuracy: 0.8643 - precision: 0.7572 - recall: 0.4250 - auc: 0.8615 - prc: 0.6715 - val_loss: 0.3832 - val_tp: 140.0000 - val_fp: 47.0000 - val_tn: 1036.0000 - val_fn: 177.0000 - val_accuracy: 0.8400 - val_precision: 0.7487 - val_recall: 0.4416 - val_auc: 0.8423 - val_prc: 0.6731
Epoch 80/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3147 - tp: 272.6667 - fp: 78.1930 - tn: 2248.8772 - fn: 298.5088 - accuracy: 0.8727 - precision: 0.7959 - recall: 0.4745 - auc: 0.8791 - prc: 0.7247 - val_loss: 0.3834 - val_tp: 137.0000 - val_fp: 44.0000 - val_tn: 1039.0000 - val_fn: 180.0000 - val_accuracy: 0.8400 - val_precision: 0.7569 - val_recall: 0.4322 - val_auc: 0.8433 - val_prc: 0.6729
Epoch 81/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3271 - tp: 263.1053 - fp: 76.0175 - tn: 2246.7895 - fn: 312.3333 - accuracy: 0.8657 - precision: 0.7911 - recall: 0.4541 - auc: 0.8715 - prc: 0.7120 - val_loss: 0.3835 - val_tp: 137.0000 - val_fp: 44.0000 - val_tn: 1039.0000 - val_fn: 180.0000 - val_accuracy: 0.8400 - val_precision: 0.7569 - val_recall: 0.4322 - val_auc: 0.8435 - val_prc: 0.6734
Epoch 82/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3240 - tp: 274.8246 - fp: 81.8772 - tn: 2236.7895 - fn: 304.7544 - accuracy: 0.8690 - precision: 0.7830 - recall: 0.4836 - auc: 0.8726 - prc: 0.7211 - val_loss: 0.3833 - val_tp: 138.0000 - val_fp: 44.0000 - val_tn: 1039.0000 - val_fn: 179.0000 - val_accuracy: 0.8407 - val_precision: 0.7582 - val_recall: 0.4353 - val_auc: 0.8435 - val_prc: 0.6732
Epoch 83/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3262 - tp: 274.2807 - fp: 79.5965 - tn: 2238.3333 - fn: 306.0351 - accuracy: 0.8662 - precision: 0.7886 - recall: 0.4764 - auc: 0.8764 - prc: 0.7194 - val_loss: 0.3821 - val_tp: 141.0000 - val_fp: 45.0000 - val_tn: 1038.0000 - val_fn: 176.0000 - val_accuracy: 0.8421 - val_precision: 0.7581 - val_recall: 0.4448 - val_auc: 0.8436 - val_prc: 0.6745
Epoch 84/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3231 - tp: 256.4211 - fp: 82.7368 - tn: 2247.0526 - fn: 312.0351 - accuracy: 0.8657 - precision: 0.7379 - recall: 0.4491 - auc: 0.8656 - prc: 0.6861 - val_loss: 0.3814 - val_tp: 141.0000 - val_fp: 46.0000 - val_tn: 1037.0000 - val_fn: 176.0000 - val_accuracy: 0.8414 - val_precision: 0.7540 - val_recall: 0.4448 - val_auc: 0.8445 - val_prc: 0.6746
Epoch 85/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3234 - tp: 274.5614 - fp: 76.7193 - tn: 2244.4386 - fn: 302.5263 - accuracy: 0.8718 - precision: 0.7883 - recall: 0.4827 - auc: 0.8749 - prc: 0.7027 - val_loss: 0.3817 - val_tp: 139.0000 - val_fp: 46.0000 - val_tn: 1037.0000 - val_fn: 178.0000 - val_accuracy: 0.8400 - val_precision: 0.7514 - val_recall: 0.4385 - val_auc: 0.8443 - val_prc: 0.6754
Epoch 86/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3217 - tp: 265.5614 - fp: 78.7895 - tn: 2246.7368 - fn: 307.1579 - accuracy: 0.8669 - precision: 0.7706 - recall: 0.4662 - auc: 0.8721 - prc: 0.7154 - val_loss: 0.3829 - val_tp: 135.0000 - val_fp: 44.0000 - val_tn: 1039.0000 - val_fn: 182.0000 - val_accuracy: 0.8386 - val_precision: 0.7542 - val_recall: 0.4259 - val_auc: 0.8438 - val_prc: 0.6753
Epoch 87/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3311 - tp: 278.5965 - fp: 77.9298 - tn: 2237.7368 - fn: 303.9825 - accuracy: 0.8645 - precision: 0.7765 - recall: 0.4647 - auc: 0.8690 - prc: 0.7100 - val_loss: 0.3837 - val_tp: 134.0000 - val_fp: 42.0000 - val_tn: 1041.0000 - val_fn: 183.0000 - val_accuracy: 0.8393 - val_precision: 0.7614 - val_recall: 0.4227 - val_auc: 0.8443 - val_prc: 0.6760
Epoch 88/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3154 - tp: 250.1228 - fp: 67.0000 - tn: 2270.7544 - fn: 310.3684 - accuracy: 0.8716 - precision: 0.7950 - recall: 0.4495 - auc: 0.8736 - prc: 0.7134 - val_loss: 0.3814 - val_tp: 140.0000 - val_fp: 46.0000 - val_tn: 1037.0000 - val_fn: 177.0000 - val_accuracy: 0.8407 - val_precision: 0.7527 - val_recall: 0.4416 - val_auc: 0.8441 - val_prc: 0.6763
Epoch 89/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3228 - tp: 274.4737 - fp: 89.8947 - tn: 2237.4035 - fn: 296.4737 - accuracy: 0.8689 - precision: 0.7488 - recall: 0.4924 - auc: 0.8725 - prc: 0.6993 - val_loss: 0.3809 - val_tp: 143.0000 - val_fp: 49.0000 - val_tn: 1034.0000 - val_fn: 174.0000 - val_accuracy: 0.8407 - val_precision: 0.7448 - val_recall: 0.4511 - val_auc: 0.8451 - val_prc: 0.6762
Epoch 90/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3305 - tp: 262.1053 - fp: 78.8947 - tn: 2252.7368 - fn: 304.5088 - accuracy: 0.8673 - precision: 0.7651 - recall: 0.4679 - auc: 0.8644 - prc: 0.6909 - val_loss: 0.3820 - val_tp: 139.0000 - val_fp: 44.0000 - val_tn: 1039.0000 - val_fn: 178.0000 - val_accuracy: 0.8414 - val_precision: 0.7596 - val_recall: 0.4385 - val_auc: 0.8443 - val_prc: 0.6759
Epoch 91/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3275 - tp: 268.1579 - fp: 77.0877 - tn: 2243.0000 - fn: 310.0000 - accuracy: 0.8654 - precision: 0.7835 - recall: 0.4532 - auc: 0.8709 - prc: 0.7014 - val_loss: 0.3815 - val_tp: 138.0000 - val_fp: 44.0000 - val_tn: 1039.0000 - val_fn: 179.0000 - val_accuracy: 0.8407 - val_precision: 0.7582 - val_recall: 0.4353 - val_auc: 0.8451 - val_prc: 0.6770
Epoch 92/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3191 - tp: 268.5263 - fp: 78.9474 - tn: 2249.0526 - fn: 301.7193 - accuracy: 0.8728 - precision: 0.7779 - recall: 0.4875 - auc: 0.8744 - prc: 0.7072 - val_loss: 0.3813 - val_tp: 140.0000 - val_fp: 46.0000 - val_tn: 1037.0000 - val_fn: 177.0000 - val_accuracy: 0.8407 - val_precision: 0.7527 - val_recall: 0.4416 - val_auc: 0.8448 - val_prc: 0.6771
Epoch 93/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3213 - tp: 261.8421 - fp: 73.8596 - tn: 2256.5614 - fn: 305.9825 - accuracy: 0.8715 - precision: 0.7822 - recall: 0.4615 - auc: 0.8677 - prc: 0.7039 - val_loss: 0.3815 - val_tp: 139.0000 - val_fp: 46.0000 - val_tn: 1037.0000 - val_fn: 178.0000 - val_accuracy: 0.8400 - val_precision: 0.7514 - val_recall: 0.4385 - val_auc: 0.8450 - val_prc: 0.6770
Epoch 94/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3266 - tp: 263.5965 - fp: 77.9474 - tn: 2247.7544 - fn: 308.9474 - accuracy: 0.8636 - precision: 0.7617 - recall: 0.4465 - auc: 0.8700 - prc: 0.6966 - val_loss: 0.3806 - val_tp: 144.0000 - val_fp: 47.0000 - val_tn: 1036.0000 - val_fn: 173.0000 - val_accuracy: 0.8429 - val_precision: 0.7539 - val_recall: 0.4543 - val_auc: 0.8453 - val_prc: 0.6768
Epoch 95/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3193 - tp: 276.4561 - fp: 83.5088 - tn: 2234.3509 - fn: 303.9298 - accuracy: 0.8687 - precision: 0.7787 - recall: 0.4837 - auc: 0.8791 - prc: 0.7237 - val_loss: 0.3825 - val_tp: 134.0000 - val_fp: 42.0000 - val_tn: 1041.0000 - val_fn: 183.0000 - val_accuracy: 0.8393 - val_precision: 0.7614 - val_recall: 0.4227 - val_auc: 0.8451 - val_prc: 0.6772
Epoch 96/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3101 - tp: 264.3509 - fp: 74.7719 - tn: 2261.5789 - fn: 297.5439 - accuracy: 0.8715 - precision: 0.7662 - recall: 0.4744 - auc: 0.8835 - prc: 0.7089 - val_loss: 0.3791 - val_tp: 145.0000 - val_fp: 52.0000 - val_tn: 1031.0000 - val_fn: 172.0000 - val_accuracy: 0.8400 - val_precision: 0.7360 - val_recall: 0.4574 - val_auc: 0.8459 - val_prc: 0.6787
Epoch 97/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3280 - tp: 270.8070 - fp: 89.4386 - tn: 2233.3158 - fn: 304.6842 - accuracy: 0.8644 - precision: 0.7570 - recall: 0.4760 - auc: 0.8703 - prc: 0.7020 - val_loss: 0.3821 - val_tp: 132.0000 - val_fp: 42.0000 - val_tn: 1041.0000 - val_fn: 185.0000 - val_accuracy: 0.8379 - val_precision: 0.7586 - val_recall: 0.4164 - val_auc: 0.8456 - val_prc: 0.6775
Epoch 98/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3178 - tp: 280.9825 - fp: 78.4035 - tn: 2242.0702 - fn: 296.7895 - accuracy: 0.8733 - precision: 0.7997 - recall: 0.4928 - auc: 0.8777 - prc: 0.7276 - val_loss: 0.3811 - val_tp: 141.0000 - val_fp: 45.0000 - val_tn: 1038.0000 - val_fn: 176.0000 - val_accuracy: 0.8421 - val_precision: 0.7581 - val_recall: 0.4448 - val_auc: 0.8458 - val_prc: 0.6774
Epoch 99/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3267 - tp: 283.5614 - fp: 78.5439 - tn: 2231.9474 - fn: 304.1930 - accuracy: 0.8679 - precision: 0.7848 - recall: 0.4838 - auc: 0.8722 - prc: 0.7174 - val_loss: 0.3820 - val_tp: 135.0000 - val_fp: 43.0000 - val_tn: 1040.0000 - val_fn: 182.0000 - val_accuracy: 0.8393 - val_precision: 0.7584 - val_recall: 0.4259 - val_auc: 0.8454 - val_prc: 0.6769
Epoch 100/100
56/56 [==============================] - 0s 2ms/step - loss: 0.3301 - tp: 281.5088 - fp: 82.2982 - tn: 2226.3333 - fn: 308.1053 - accuracy: 0.8628 - precision: 0.7775 - recall: 0.4699 - auc: 0.8723 - prc: 0.7158 - val_loss: 0.3826 - val_tp: 133.0000 - val_fp: 40.0000 - val_tn: 1043.0000 - val_fn: 184.0000 - val_accuracy: 0.8400 - val_precision: 0.7688 - val_recall: 0.4196 - val_auc: 0.8456 - val_prc: 0.6784
CPU times: user 18.7 s, sys: 2.93 s, total: 21.7 s
Wall time: 12.7 s


model1.summary()

Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense (Dense)                (None, 16)                192       
_________________________________________________________________
dense_1 (Dense)              (None, 1)                 17        
=================================================================
Total params: 209
Trainable params: 209
Non-trainable params: 0
_________________________________________________________________


history_df = pd.DataFrame(history1.history)
history_df['epoch']=history1.epoch
display(history_df)
train_acc = history_df.loc[99,'accuracy']
train_recall = history_df.loc[99,'recall']
train_loss = history_df.loc[99,'loss']


results1=model1.evaluate(X_test, y_test.values)
#print(model1.metrics_names)
#print(results1)

results_df = pd.DataFrame(results1, index=model1.metrics_names, columns=['model1'])

results_df

94/94 [==============================] - 1s 1ms/step - loss: 0.3512 - tp: 274.0000 - fp: 85.0000 - tn: 2304.0000 - fn: 337.0000 - accuracy: 0.8593 - precision: 0.7632 - recall: 0.4484 - auc: 0.8482 - prc: 0.6746


plt.figure(figsize=(10,10))
plot_metrics(history1)


# ANN return continuous nos from 0 to 1 as output
# we use a threshold of 0.5 to classify the output as 0 or 1
# the code below converts the true/ false statement into 1/0 by forcing type conversion to int32


y_predict = (model1.predict(X_test) > THRESHOLD).astype('int32')

make_confusion_matrix(model1,y_test,y_predict, cmap='magma_r')


print(f'Model test loss is: {results_df.loc["loss","model1"]:0.4f}, train loss is {train_loss:0.4f}')
print(f'Model test accuracy is: {results_df.loc["accuracy","model1"]:0.4f}, train accuracy is {train_acc:0.4f}')
print(f'Model test recall is: {results_df.loc["recall","model1"]:0.4f}, train recall is {train_recall:0.4f}')

Model test loss is: 0.3512, train loss is 0.3220
Model test accuracy is: 0.8593, train accuracy is 0.8675
Model test recall is: 0.4484, train recall is 0.4680


# Source: https://www.tensorflow.org/tutorials/structured_data/imbalanced_data


# Scaling by total/2 helps keep the loss to a similar magnitude.
# The sum of the weights of all examples stays the same.
weight_for_0 = (1 / neg)*(total)/2.0 
weight_for_1 = (1 / pos)*(total)/2.0

class_weight = {0: weight_for_0, 1: weight_for_1}

print('Weight for class 0: {:.2f}'.format(weight_for_0))
print('Weight for class 1: {:.2f}'.format(weight_for_1))

Weight for class 0: 0.63
Weight for class 1: 2.45


%%time 

model2 = make_model(dropout=True, learning_rate=0.001)

history2 = model2.fit(X_train, y_train, epochs=EPOCHS+100, batch_size=BATCH_SIZE, use_multiprocessing=True, validation_split=0.2, class_weight=class_weight)

WARNING:tensorflow:From /Users/tusharsinha/anaconda3/envs/myenv39/lib/python3.9/site-packages/tensorflow/python/ops/array_ops.py:5043: calling gather (from tensorflow.python.ops.array_ops) with validate_indices is deprecated and will be removed in a future version.
Instructions for updating:
The `validate_indices` argument has no effect. Indices are always validated on CPU and never validated on GPU.
Epoch 1/200
56/56 [==============================] - 3s 20ms/step - loss: 0.6775 - tp: 635.5088 - fp: 1109.3158 - tn: 3597.9649 - fn: 555.4561 - accuracy: 0.7307 - precision: 0.3991 - recall: 0.5257 - auc: 0.7374 - prc: 0.4854 - val_loss: 0.6453 - val_tp: 221.0000 - val_fp: 427.0000 - val_tn: 656.0000 - val_fn: 96.0000 - val_accuracy: 0.6264 - val_precision: 0.3410 - val_recall: 0.6972 - val_auc: 0.7201 - val_prc: 0.4352
Epoch 2/200
56/56 [==============================] - 0s 2ms/step - loss: 0.6468 - tp: 333.7368 - fp: 913.6140 - tn: 1419.6667 - fn: 231.2281 - accuracy: 0.6016 - precision: 0.2580 - recall: 0.5797 - auc: 0.6346 - prc: 0.3321 - val_loss: 0.6358 - val_tp: 231.0000 - val_fp: 407.0000 - val_tn: 676.0000 - val_fn: 86.0000 - val_accuracy: 0.6479 - val_precision: 0.3621 - val_recall: 0.7287 - val_auc: 0.7421 - val_prc: 0.4409
Epoch 3/200
56/56 [==============================] - 0s 2ms/step - loss: 0.6297 - tp: 395.5789 - fp: 844.6491 - tn: 1462.4211 - fn: 195.5965 - accuracy: 0.6412 - precision: 0.3216 - recall: 0.6692 - auc: 0.7077 - prc: 0.4190 - val_loss: 0.6205 - val_tp: 226.0000 - val_fp: 362.0000 - val_tn: 721.0000 - val_fn: 91.0000 - val_accuracy: 0.6764 - val_precision: 0.3844 - val_recall: 0.7129 - val_auc: 0.7498 - val_prc: 0.4447
Epoch 4/200
56/56 [==============================] - 0s 2ms/step - loss: 0.6096 - tp: 349.7719 - fp: 766.1579 - tn: 1574.6140 - fn: 207.7018 - accuracy: 0.6587 - precision: 0.3082 - recall: 0.6459 - auc: 0.7100 - prc: 0.3656 - val_loss: 0.6131 - val_tp: 229.0000 - val_fp: 343.0000 - val_tn: 740.0000 - val_fn: 88.0000 - val_accuracy: 0.6921 - val_precision: 0.4003 - val_recall: 0.7224 - val_auc: 0.7538 - val_prc: 0.4466
Epoch 5/200
56/56 [==============================] - 0s 2ms/step - loss: 0.6037 - tp: 377.4912 - fp: 736.1053 - tn: 1593.8070 - fn: 190.8421 - accuracy: 0.6771 - precision: 0.3351 - recall: 0.6680 - auc: 0.7272 - prc: 0.4018 - val_loss: 0.6101 - val_tp: 232.0000 - val_fp: 343.0000 - val_tn: 740.0000 - val_fn: 85.0000 - val_accuracy: 0.6943 - val_precision: 0.4035 - val_recall: 0.7319 - val_auc: 0.7581 - val_prc: 0.4491
Epoch 6/200
56/56 [==============================] - 0s 2ms/step - loss: 0.6024 - tp: 381.6667 - fp: 729.6140 - tn: 1588.4035 - fn: 198.5614 - accuracy: 0.6816 - precision: 0.3409 - recall: 0.6576 - auc: 0.7317 - prc: 0.4000 - val_loss: 0.6037 - val_tp: 229.0000 - val_fp: 334.0000 - val_tn: 749.0000 - val_fn: 88.0000 - val_accuracy: 0.6986 - val_precision: 0.4067 - val_recall: 0.7224 - val_auc: 0.7609 - val_prc: 0.4541
Epoch 7/200
56/56 [==============================] - 0s 2ms/step - loss: 0.6083 - tp: 394.0526 - fp: 718.4211 - tn: 1591.1930 - fn: 194.5789 - accuracy: 0.6852 - precision: 0.3566 - recall: 0.6608 - auc: 0.7345 - prc: 0.4269 - val_loss: 0.5964 - val_tp: 229.0000 - val_fp: 319.0000 - val_tn: 764.0000 - val_fn: 88.0000 - val_accuracy: 0.7093 - val_precision: 0.4179 - val_recall: 0.7224 - val_auc: 0.7625 - val_prc: 0.4593
Epoch 8/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5857 - tp: 375.3684 - fp: 655.3158 - tn: 1684.5789 - fn: 182.9825 - accuracy: 0.7138 - precision: 0.3668 - recall: 0.6801 - auc: 0.7478 - prc: 0.4144 - val_loss: 0.5898 - val_tp: 224.0000 - val_fp: 311.0000 - val_tn: 772.0000 - val_fn: 93.0000 - val_accuracy: 0.7114 - val_precision: 0.4187 - val_recall: 0.7066 - val_auc: 0.7642 - val_prc: 0.4639
Epoch 9/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5872 - tp: 381.9123 - fp: 687.7719 - tn: 1644.8947 - fn: 183.6667 - accuracy: 0.6983 - precision: 0.3543 - recall: 0.6741 - auc: 0.7483 - prc: 0.4424 - val_loss: 0.5917 - val_tp: 231.0000 - val_fp: 323.0000 - val_tn: 760.0000 - val_fn: 86.0000 - val_accuracy: 0.7079 - val_precision: 0.4170 - val_recall: 0.7287 - val_auc: 0.7676 - val_prc: 0.4707
Epoch 10/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5783 - tp: 389.1404 - fp: 699.6140 - tn: 1628.8772 - fn: 180.6140 - accuracy: 0.6981 - precision: 0.3609 - recall: 0.6891 - auc: 0.7618 - prc: 0.4507 - val_loss: 0.5872 - val_tp: 230.0000 - val_fp: 325.0000 - val_tn: 758.0000 - val_fn: 87.0000 - val_accuracy: 0.7057 - val_precision: 0.4144 - val_recall: 0.7256 - val_auc: 0.7704 - val_prc: 0.4784
Epoch 11/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5870 - tp: 387.2281 - fp: 690.3509 - tn: 1636.2456 - fn: 184.4211 - accuracy: 0.7021 - precision: 0.3656 - recall: 0.6775 - auc: 0.7540 - prc: 0.4537 - val_loss: 0.5785 - val_tp: 225.0000 - val_fp: 303.0000 - val_tn: 780.0000 - val_fn: 92.0000 - val_accuracy: 0.7179 - val_precision: 0.4261 - val_recall: 0.7098 - val_auc: 0.7739 - val_prc: 0.4873
Epoch 12/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5696 - tp: 406.6842 - fp: 672.3158 - tn: 1659.4386 - fn: 159.8070 - accuracy: 0.7190 - precision: 0.3827 - recall: 0.7331 - auc: 0.7752 - prc: 0.4703 - val_loss: 0.5749 - val_tp: 224.0000 - val_fp: 301.0000 - val_tn: 782.0000 - val_fn: 93.0000 - val_accuracy: 0.7186 - val_precision: 0.4267 - val_recall: 0.7066 - val_auc: 0.7765 - val_prc: 0.4925
Epoch 13/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5838 - tp: 390.5263 - fp: 669.1404 - tn: 1654.7719 - fn: 183.8070 - accuracy: 0.7060 - precision: 0.3733 - recall: 0.6838 - auc: 0.7612 - prc: 0.4568 - val_loss: 0.5718 - val_tp: 226.0000 - val_fp: 296.0000 - val_tn: 787.0000 - val_fn: 91.0000 - val_accuracy: 0.7236 - val_precision: 0.4330 - val_recall: 0.7129 - val_auc: 0.7803 - val_prc: 0.5005
Epoch 14/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5963 - tp: 417.3509 - fp: 658.2105 - tn: 1655.5965 - fn: 167.0877 - accuracy: 0.7091 - precision: 0.3910 - recall: 0.7096 - auc: 0.7582 - prc: 0.4386 - val_loss: 0.5636 - val_tp: 223.0000 - val_fp: 287.0000 - val_tn: 796.0000 - val_fn: 94.0000 - val_accuracy: 0.7279 - val_precision: 0.4373 - val_recall: 0.7035 - val_auc: 0.7830 - val_prc: 0.5068
Epoch 15/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5610 - tp: 411.9123 - fp: 636.9474 - tn: 1685.3509 - fn: 164.0351 - accuracy: 0.7207 - precision: 0.3882 - recall: 0.7177 - auc: 0.7839 - prc: 0.4830 - val_loss: 0.5622 - val_tp: 223.0000 - val_fp: 292.0000 - val_tn: 791.0000 - val_fn: 94.0000 - val_accuracy: 0.7243 - val_precision: 0.4330 - val_recall: 0.7035 - val_auc: 0.7853 - val_prc: 0.5144
Epoch 16/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5699 - tp: 389.9123 - fp: 644.7895 - tn: 1684.1228 - fn: 179.4211 - accuracy: 0.7150 - precision: 0.3725 - recall: 0.6719 - auc: 0.7647 - prc: 0.4540 - val_loss: 0.5614 - val_tp: 225.0000 - val_fp: 292.0000 - val_tn: 791.0000 - val_fn: 92.0000 - val_accuracy: 0.7257 - val_precision: 0.4352 - val_recall: 0.7098 - val_auc: 0.7878 - val_prc: 0.5192
Epoch 17/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5642 - tp: 407.9649 - fp: 636.9474 - tn: 1691.9825 - fn: 161.3509 - accuracy: 0.7253 - precision: 0.3903 - recall: 0.7128 - auc: 0.7774 - prc: 0.4839 - val_loss: 0.5583 - val_tp: 225.0000 - val_fp: 290.0000 - val_tn: 793.0000 - val_fn: 92.0000 - val_accuracy: 0.7271 - val_precision: 0.4369 - val_recall: 0.7098 - val_auc: 0.7897 - val_prc: 0.5229
Epoch 18/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5769 - tp: 399.8070 - fp: 636.1579 - tn: 1685.8246 - fn: 176.4561 - accuracy: 0.7179 - precision: 0.3887 - recall: 0.6870 - auc: 0.7720 - prc: 0.4731 - val_loss: 0.5549 - val_tp: 227.0000 - val_fp: 284.0000 - val_tn: 799.0000 - val_fn: 90.0000 - val_accuracy: 0.7329 - val_precision: 0.4442 - val_recall: 0.7161 - val_auc: 0.7903 - val_prc: 0.5255
Epoch 19/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5511 - tp: 418.5965 - fp: 640.0351 - tn: 1683.7193 - fn: 155.8947 - accuracy: 0.7280 - precision: 0.3997 - recall: 0.7348 - auc: 0.7967 - prc: 0.4986 - val_loss: 0.5537 - val_tp: 227.0000 - val_fp: 283.0000 - val_tn: 800.0000 - val_fn: 90.0000 - val_accuracy: 0.7336 - val_precision: 0.4451 - val_recall: 0.7161 - val_auc: 0.7929 - val_prc: 0.5323
Epoch 20/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5598 - tp: 409.6842 - fp: 652.4386 - tn: 1671.6667 - fn: 164.4561 - accuracy: 0.7168 - precision: 0.3889 - recall: 0.7240 - auc: 0.7844 - prc: 0.4969 - val_loss: 0.5511 - val_tp: 225.0000 - val_fp: 280.0000 - val_tn: 803.0000 - val_fn: 92.0000 - val_accuracy: 0.7343 - val_precision: 0.4455 - val_recall: 0.7098 - val_auc: 0.7946 - val_prc: 0.5375
Epoch 21/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5595 - tp: 391.7895 - fp: 627.6842 - tn: 1703.4386 - fn: 175.3333 - accuracy: 0.7200 - precision: 0.3814 - recall: 0.6956 - auc: 0.7803 - prc: 0.4888 - val_loss: 0.5520 - val_tp: 227.0000 - val_fp: 284.0000 - val_tn: 799.0000 - val_fn: 90.0000 - val_accuracy: 0.7329 - val_precision: 0.4442 - val_recall: 0.7161 - val_auc: 0.7957 - val_prc: 0.5398
Epoch 22/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5595 - tp: 398.0000 - fp: 625.6316 - tn: 1700.5789 - fn: 174.0351 - accuracy: 0.7194 - precision: 0.3805 - recall: 0.6842 - auc: 0.7811 - prc: 0.4937 - val_loss: 0.5469 - val_tp: 226.0000 - val_fp: 271.0000 - val_tn: 812.0000 - val_fn: 91.0000 - val_accuracy: 0.7414 - val_precision: 0.4547 - val_recall: 0.7129 - val_auc: 0.7971 - val_prc: 0.5447
Epoch 23/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5623 - tp: 398.2807 - fp: 640.0175 - tn: 1692.7018 - fn: 167.2456 - accuracy: 0.7174 - precision: 0.3829 - recall: 0.7070 - auc: 0.7795 - prc: 0.4830 - val_loss: 0.5473 - val_tp: 226.0000 - val_fp: 273.0000 - val_tn: 810.0000 - val_fn: 91.0000 - val_accuracy: 0.7400 - val_precision: 0.4529 - val_recall: 0.7129 - val_auc: 0.7987 - val_prc: 0.5467
Epoch 24/200
56/56 [==============================] - 0s 1ms/step - loss: 0.5415 - tp: 405.2281 - fp: 589.5965 - tn: 1735.0526 - fn: 168.3684 - accuracy: 0.7409 - precision: 0.4103 - recall: 0.7061 - auc: 0.8005 - prc: 0.5280 - val_loss: 0.5463 - val_tp: 228.0000 - val_fp: 274.0000 - val_tn: 809.0000 - val_fn: 89.0000 - val_accuracy: 0.7407 - val_precision: 0.4542 - val_recall: 0.7192 - val_auc: 0.8004 - val_prc: 0.5521
Epoch 25/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5400 - tp: 419.1754 - fp: 611.3509 - tn: 1706.4386 - fn: 161.2807 - accuracy: 0.7361 - precision: 0.4122 - recall: 0.7278 - auc: 0.8052 - prc: 0.5404 - val_loss: 0.5410 - val_tp: 225.0000 - val_fp: 268.0000 - val_tn: 815.0000 - val_fn: 92.0000 - val_accuracy: 0.7429 - val_precision: 0.4564 - val_recall: 0.7098 - val_auc: 0.8006 - val_prc: 0.5538
Epoch 26/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5414 - tp: 398.7895 - fp: 595.6491 - tn: 1731.5965 - fn: 172.2105 - accuracy: 0.7331 - precision: 0.3981 - recall: 0.6995 - auc: 0.7999 - prc: 0.5316 - val_loss: 0.5390 - val_tp: 225.0000 - val_fp: 271.0000 - val_tn: 812.0000 - val_fn: 92.0000 - val_accuracy: 0.7407 - val_precision: 0.4536 - val_recall: 0.7098 - val_auc: 0.8018 - val_prc: 0.5586
Epoch 27/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5751 - tp: 409.1579 - fp: 612.7018 - tn: 1695.9474 - fn: 180.4386 - accuracy: 0.7274 - precision: 0.4049 - recall: 0.6936 - auc: 0.7759 - prc: 0.4883 - val_loss: 0.5398 - val_tp: 227.0000 - val_fp: 268.0000 - val_tn: 815.0000 - val_fn: 90.0000 - val_accuracy: 0.7443 - val_precision: 0.4586 - val_recall: 0.7161 - val_auc: 0.8028 - val_prc: 0.5610
Epoch 28/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5463 - tp: 401.1579 - fp: 579.8947 - tn: 1746.8596 - fn: 170.3333 - accuracy: 0.7413 - precision: 0.4093 - recall: 0.7135 - auc: 0.7941 - prc: 0.5228 - val_loss: 0.5378 - val_tp: 227.0000 - val_fp: 268.0000 - val_tn: 815.0000 - val_fn: 90.0000 - val_accuracy: 0.7443 - val_precision: 0.4586 - val_recall: 0.7161 - val_auc: 0.8038 - val_prc: 0.5646
Epoch 29/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5471 - tp: 392.5263 - fp: 577.0351 - tn: 1751.3333 - fn: 177.3509 - accuracy: 0.7397 - precision: 0.4010 - recall: 0.6872 - auc: 0.7929 - prc: 0.4976 - val_loss: 0.5355 - val_tp: 227.0000 - val_fp: 267.0000 - val_tn: 816.0000 - val_fn: 90.0000 - val_accuracy: 0.7450 - val_precision: 0.4595 - val_recall: 0.7161 - val_auc: 0.8046 - val_prc: 0.5664
Epoch 30/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5444 - tp: 396.5088 - fp: 593.1579 - tn: 1739.5088 - fn: 169.0702 - accuracy: 0.7353 - precision: 0.3880 - recall: 0.6869 - auc: 0.7893 - prc: 0.5100 - val_loss: 0.5342 - val_tp: 226.0000 - val_fp: 264.0000 - val_tn: 819.0000 - val_fn: 91.0000 - val_accuracy: 0.7464 - val_precision: 0.4612 - val_recall: 0.7129 - val_auc: 0.8062 - val_prc: 0.5708
Epoch 31/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5548 - tp: 391.9649 - fp: 603.9298 - tn: 1722.2632 - fn: 180.0877 - accuracy: 0.7243 - precision: 0.3811 - recall: 0.6703 - auc: 0.7811 - prc: 0.4964 - val_loss: 0.5331 - val_tp: 226.0000 - val_fp: 264.0000 - val_tn: 819.0000 - val_fn: 91.0000 - val_accuracy: 0.7464 - val_precision: 0.4612 - val_recall: 0.7129 - val_auc: 0.8070 - val_prc: 0.5757
Epoch 32/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5314 - tp: 402.2982 - fp: 583.1053 - tn: 1752.2281 - fn: 160.6140 - accuracy: 0.7449 - precision: 0.4087 - recall: 0.7291 - auc: 0.8055 - prc: 0.5315 - val_loss: 0.5309 - val_tp: 227.0000 - val_fp: 263.0000 - val_tn: 820.0000 - val_fn: 90.0000 - val_accuracy: 0.7479 - val_precision: 0.4633 - val_recall: 0.7161 - val_auc: 0.8084 - val_prc: 0.5785
Epoch 33/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5566 - tp: 415.0175 - fp: 585.4211 - tn: 1729.5439 - fn: 168.2632 - accuracy: 0.7434 - precision: 0.4266 - recall: 0.7155 - auc: 0.7922 - prc: 0.5158 - val_loss: 0.5304 - val_tp: 226.0000 - val_fp: 261.0000 - val_tn: 822.0000 - val_fn: 91.0000 - val_accuracy: 0.7486 - val_precision: 0.4641 - val_recall: 0.7129 - val_auc: 0.8083 - val_prc: 0.5793
Epoch 34/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5477 - tp: 396.1228 - fp: 572.3684 - tn: 1757.1053 - fn: 172.6491 - accuracy: 0.7458 - precision: 0.4109 - recall: 0.6996 - auc: 0.7943 - prc: 0.4912 - val_loss: 0.5291 - val_tp: 225.0000 - val_fp: 262.0000 - val_tn: 821.0000 - val_fn: 92.0000 - val_accuracy: 0.7471 - val_precision: 0.4620 - val_recall: 0.7098 - val_auc: 0.8099 - val_prc: 0.5843
Epoch 35/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5519 - tp: 401.6491 - fp: 574.6667 - tn: 1749.5789 - fn: 172.3509 - accuracy: 0.7417 - precision: 0.4067 - recall: 0.6904 - auc: 0.7888 - prc: 0.5080 - val_loss: 0.5293 - val_tp: 223.0000 - val_fp: 260.0000 - val_tn: 823.0000 - val_fn: 94.0000 - val_accuracy: 0.7471 - val_precision: 0.4617 - val_recall: 0.7035 - val_auc: 0.8106 - val_prc: 0.5863
Epoch 36/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5453 - tp: 410.0526 - fp: 582.6316 - tn: 1735.3158 - fn: 170.2456 - accuracy: 0.7437 - precision: 0.4258 - recall: 0.7104 - auc: 0.8044 - prc: 0.5289 - val_loss: 0.5229 - val_tp: 221.0000 - val_fp: 255.0000 - val_tn: 828.0000 - val_fn: 96.0000 - val_accuracy: 0.7493 - val_precision: 0.4643 - val_recall: 0.6972 - val_auc: 0.8107 - val_prc: 0.5878
Epoch 37/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5417 - tp: 401.2105 - fp: 567.5789 - tn: 1754.4737 - fn: 174.9825 - accuracy: 0.7437 - precision: 0.4144 - recall: 0.7002 - auc: 0.7987 - prc: 0.5182 - val_loss: 0.5292 - val_tp: 225.0000 - val_fp: 267.0000 - val_tn: 816.0000 - val_fn: 92.0000 - val_accuracy: 0.7436 - val_precision: 0.4573 - val_recall: 0.7098 - val_auc: 0.8117 - val_prc: 0.5884
Epoch 38/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5409 - tp: 404.9825 - fp: 579.9298 - tn: 1734.7895 - fn: 178.5439 - accuracy: 0.7345 - precision: 0.4027 - recall: 0.6876 - auc: 0.7983 - prc: 0.5448 - val_loss: 0.5245 - val_tp: 224.0000 - val_fp: 260.0000 - val_tn: 823.0000 - val_fn: 93.0000 - val_accuracy: 0.7479 - val_precision: 0.4628 - val_recall: 0.7066 - val_auc: 0.8127 - val_prc: 0.5919
Epoch 39/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5407 - tp: 392.8421 - fp: 570.0175 - tn: 1754.2982 - fn: 181.0877 - accuracy: 0.7385 - precision: 0.3995 - recall: 0.6906 - auc: 0.7974 - prc: 0.5183 - val_loss: 0.5235 - val_tp: 224.0000 - val_fp: 257.0000 - val_tn: 826.0000 - val_fn: 93.0000 - val_accuracy: 0.7500 - val_precision: 0.4657 - val_recall: 0.7066 - val_auc: 0.8126 - val_prc: 0.5932
Epoch 40/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5495 - tp: 385.2105 - fp: 557.4561 - tn: 1771.4386 - fn: 184.1404 - accuracy: 0.7398 - precision: 0.3973 - recall: 0.6721 - auc: 0.7841 - prc: 0.5106 - val_loss: 0.5252 - val_tp: 226.0000 - val_fp: 260.0000 - val_tn: 823.0000 - val_fn: 91.0000 - val_accuracy: 0.7493 - val_precision: 0.4650 - val_recall: 0.7129 - val_auc: 0.8133 - val_prc: 0.5952
Epoch 41/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5588 - tp: 380.0877 - fp: 582.1930 - tn: 1749.9474 - fn: 186.0175 - accuracy: 0.7331 - precision: 0.3966 - recall: 0.6604 - auc: 0.7840 - prc: 0.4990 - val_loss: 0.5206 - val_tp: 225.0000 - val_fp: 257.0000 - val_tn: 826.0000 - val_fn: 92.0000 - val_accuracy: 0.7507 - val_precision: 0.4668 - val_recall: 0.7098 - val_auc: 0.8141 - val_prc: 0.5967
Epoch 42/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5452 - tp: 408.5789 - fp: 588.7018 - tn: 1727.1930 - fn: 173.7719 - accuracy: 0.7385 - precision: 0.4130 - recall: 0.7032 - auc: 0.7989 - prc: 0.5353 - val_loss: 0.5240 - val_tp: 226.0000 - val_fp: 263.0000 - val_tn: 820.0000 - val_fn: 91.0000 - val_accuracy: 0.7471 - val_precision: 0.4622 - val_recall: 0.7129 - val_auc: 0.8150 - val_prc: 0.5980
Epoch 43/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5346 - tp: 385.4035 - fp: 561.8070 - tn: 1774.3684 - fn: 176.6667 - accuracy: 0.7485 - precision: 0.4068 - recall: 0.6918 - auc: 0.7994 - prc: 0.5317 - val_loss: 0.5225 - val_tp: 227.0000 - val_fp: 257.0000 - val_tn: 826.0000 - val_fn: 90.0000 - val_accuracy: 0.7521 - val_precision: 0.4690 - val_recall: 0.7161 - val_auc: 0.8149 - val_prc: 0.5984
Epoch 44/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5434 - tp: 389.2281 - fp: 573.9825 - tn: 1756.6316 - fn: 178.4035 - accuracy: 0.7377 - precision: 0.4004 - recall: 0.6811 - auc: 0.7963 - prc: 0.5299 - val_loss: 0.5215 - val_tp: 226.0000 - val_fp: 257.0000 - val_tn: 826.0000 - val_fn: 91.0000 - val_accuracy: 0.7514 - val_precision: 0.4679 - val_recall: 0.7129 - val_auc: 0.8156 - val_prc: 0.6000
Epoch 45/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5301 - tp: 409.5789 - fp: 542.5614 - tn: 1778.2456 - fn: 167.8596 - accuracy: 0.7611 - precision: 0.4387 - recall: 0.7230 - auc: 0.8114 - prc: 0.5546 - val_loss: 0.5261 - val_tp: 230.0000 - val_fp: 262.0000 - val_tn: 821.0000 - val_fn: 87.0000 - val_accuracy: 0.7507 - val_precision: 0.4675 - val_recall: 0.7256 - val_auc: 0.8163 - val_prc: 0.6020
Epoch 46/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5241 - tp: 423.3333 - fp: 575.0702 - tn: 1747.4386 - fn: 152.4035 - accuracy: 0.7505 - precision: 0.4221 - recall: 0.7431 - auc: 0.8153 - prc: 0.5643 - val_loss: 0.5167 - val_tp: 226.0000 - val_fp: 251.0000 - val_tn: 832.0000 - val_fn: 91.0000 - val_accuracy: 0.7557 - val_precision: 0.4738 - val_recall: 0.7129 - val_auc: 0.8166 - val_prc: 0.6042
Epoch 47/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5367 - tp: 394.6316 - fp: 534.4035 - tn: 1794.4561 - fn: 174.7544 - accuracy: 0.7580 - precision: 0.4238 - recall: 0.7065 - auc: 0.8054 - prc: 0.5095 - val_loss: 0.5200 - val_tp: 228.0000 - val_fp: 258.0000 - val_tn: 825.0000 - val_fn: 89.0000 - val_accuracy: 0.7521 - val_precision: 0.4691 - val_recall: 0.7192 - val_auc: 0.8172 - val_prc: 0.6060
Epoch 48/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5519 - tp: 397.1053 - fp: 565.5088 - tn: 1753.9474 - fn: 181.6842 - accuracy: 0.7404 - precision: 0.4127 - recall: 0.6862 - auc: 0.7946 - prc: 0.5215 - val_loss: 0.5157 - val_tp: 220.0000 - val_fp: 246.0000 - val_tn: 837.0000 - val_fn: 97.0000 - val_accuracy: 0.7550 - val_precision: 0.4721 - val_recall: 0.6940 - val_auc: 0.8170 - val_prc: 0.6072
Epoch 49/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5470 - tp: 378.0351 - fp: 527.4386 - tn: 1805.6667 - fn: 187.1053 - accuracy: 0.7531 - precision: 0.4146 - recall: 0.6573 - auc: 0.7911 - prc: 0.5133 - val_loss: 0.5130 - val_tp: 221.0000 - val_fp: 242.0000 - val_tn: 841.0000 - val_fn: 96.0000 - val_accuracy: 0.7586 - val_precision: 0.4773 - val_recall: 0.6972 - val_auc: 0.8177 - val_prc: 0.6107
Epoch 50/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5314 - tp: 393.3333 - fp: 531.5614 - tn: 1796.1754 - fn: 177.1754 - accuracy: 0.7565 - precision: 0.4294 - recall: 0.6900 - auc: 0.8145 - prc: 0.5279 - val_loss: 0.5099 - val_tp: 220.0000 - val_fp: 239.0000 - val_tn: 844.0000 - val_fn: 97.0000 - val_accuracy: 0.7600 - val_precision: 0.4793 - val_recall: 0.6940 - val_auc: 0.8174 - val_prc: 0.6103
Epoch 51/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5393 - tp: 396.1579 - fp: 545.5263 - tn: 1780.2632 - fn: 176.2982 - accuracy: 0.7472 - precision: 0.4156 - recall: 0.6815 - auc: 0.8018 - prc: 0.5306 - val_loss: 0.5168 - val_tp: 226.0000 - val_fp: 253.0000 - val_tn: 830.0000 - val_fn: 91.0000 - val_accuracy: 0.7543 - val_precision: 0.4718 - val_recall: 0.7129 - val_auc: 0.8182 - val_prc: 0.6123
Epoch 52/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5355 - tp: 408.3684 - fp: 555.6842 - tn: 1768.8246 - fn: 165.3684 - accuracy: 0.7501 - precision: 0.4268 - recall: 0.7176 - auc: 0.8070 - prc: 0.5586 - val_loss: 0.5160 - val_tp: 228.0000 - val_fp: 250.0000 - val_tn: 833.0000 - val_fn: 89.0000 - val_accuracy: 0.7579 - val_precision: 0.4770 - val_recall: 0.7192 - val_auc: 0.8188 - val_prc: 0.6137
Epoch 53/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5404 - tp: 397.8772 - fp: 543.4912 - tn: 1781.8070 - fn: 175.0702 - accuracy: 0.7502 - precision: 0.4198 - recall: 0.6961 - auc: 0.8008 - prc: 0.5423 - val_loss: 0.5147 - val_tp: 224.0000 - val_fp: 248.0000 - val_tn: 835.0000 - val_fn: 93.0000 - val_accuracy: 0.7564 - val_precision: 0.4746 - val_recall: 0.7066 - val_auc: 0.8190 - val_prc: 0.6149
Epoch 54/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5264 - tp: 396.0000 - fp: 530.9649 - tn: 1800.8772 - fn: 170.4035 - accuracy: 0.7569 - precision: 0.4179 - recall: 0.6990 - auc: 0.8079 - prc: 0.5173 - val_loss: 0.5111 - val_tp: 224.0000 - val_fp: 246.0000 - val_tn: 837.0000 - val_fn: 93.0000 - val_accuracy: 0.7579 - val_precision: 0.4766 - val_recall: 0.7066 - val_auc: 0.8192 - val_prc: 0.6156
Epoch 55/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5158 - tp: 387.5965 - fp: 545.4737 - tn: 1795.6316 - fn: 169.5439 - accuracy: 0.7590 - precision: 0.4212 - recall: 0.7116 - auc: 0.8170 - prc: 0.5387 - val_loss: 0.5150 - val_tp: 227.0000 - val_fp: 252.0000 - val_tn: 831.0000 - val_fn: 90.0000 - val_accuracy: 0.7557 - val_precision: 0.4739 - val_recall: 0.7161 - val_auc: 0.8196 - val_prc: 0.6168
Epoch 56/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5406 - tp: 391.8947 - fp: 536.4035 - tn: 1784.6667 - fn: 185.2807 - accuracy: 0.7542 - precision: 0.4243 - recall: 0.6802 - auc: 0.7992 - prc: 0.5303 - val_loss: 0.5157 - val_tp: 227.0000 - val_fp: 252.0000 - val_tn: 831.0000 - val_fn: 90.0000 - val_accuracy: 0.7557 - val_precision: 0.4739 - val_recall: 0.7161 - val_auc: 0.8199 - val_prc: 0.6174
Epoch 57/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5414 - tp: 403.4211 - fp: 557.6667 - tn: 1763.4211 - fn: 173.7368 - accuracy: 0.7475 - precision: 0.4169 - recall: 0.6981 - auc: 0.8038 - prc: 0.5205 - val_loss: 0.5111 - val_tp: 225.0000 - val_fp: 242.0000 - val_tn: 841.0000 - val_fn: 92.0000 - val_accuracy: 0.7614 - val_precision: 0.4818 - val_recall: 0.7098 - val_auc: 0.8208 - val_prc: 0.6201
Epoch 58/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5360 - tp: 405.7193 - fp: 527.9298 - tn: 1790.3158 - fn: 174.2807 - accuracy: 0.7611 - precision: 0.4369 - recall: 0.7046 - auc: 0.8051 - prc: 0.5271 - val_loss: 0.5042 - val_tp: 218.0000 - val_fp: 235.0000 - val_tn: 848.0000 - val_fn: 99.0000 - val_accuracy: 0.7614 - val_precision: 0.4812 - val_recall: 0.6877 - val_auc: 0.8218 - val_prc: 0.6240
Epoch 59/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5281 - tp: 410.6667 - fp: 532.4912 - tn: 1786.9474 - fn: 168.1404 - accuracy: 0.7657 - precision: 0.4473 - recall: 0.7263 - auc: 0.8188 - prc: 0.5512 - val_loss: 0.5056 - val_tp: 220.0000 - val_fp: 236.0000 - val_tn: 847.0000 - val_fn: 97.0000 - val_accuracy: 0.7621 - val_precision: 0.4825 - val_recall: 0.6940 - val_auc: 0.8214 - val_prc: 0.6238
Epoch 60/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5489 - tp: 397.4211 - fp: 508.8070 - tn: 1800.5263 - fn: 191.4912 - accuracy: 0.7558 - precision: 0.4398 - recall: 0.6715 - auc: 0.8030 - prc: 0.5308 - val_loss: 0.5107 - val_tp: 225.0000 - val_fp: 246.0000 - val_tn: 837.0000 - val_fn: 92.0000 - val_accuracy: 0.7586 - val_precision: 0.4777 - val_recall: 0.7098 - val_auc: 0.8220 - val_prc: 0.6240
Epoch 61/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5203 - tp: 397.5614 - fp: 519.4035 - tn: 1812.7018 - fn: 168.5789 - accuracy: 0.7607 - precision: 0.4281 - recall: 0.7027 - auc: 0.8156 - prc: 0.5304 - val_loss: 0.5018 - val_tp: 218.0000 - val_fp: 234.0000 - val_tn: 849.0000 - val_fn: 99.0000 - val_accuracy: 0.7621 - val_precision: 0.4823 - val_recall: 0.6877 - val_auc: 0.8215 - val_prc: 0.6244
Epoch 62/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5494 - tp: 375.1754 - fp: 523.5965 - tn: 1804.4737 - fn: 195.0000 - accuracy: 0.7543 - precision: 0.4147 - recall: 0.6470 - auc: 0.7889 - prc: 0.4908 - val_loss: 0.5080 - val_tp: 225.0000 - val_fp: 243.0000 - val_tn: 840.0000 - val_fn: 92.0000 - val_accuracy: 0.7607 - val_precision: 0.4808 - val_recall: 0.7098 - val_auc: 0.8231 - val_prc: 0.6271
Epoch 63/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5437 - tp: 380.0702 - fp: 532.5789 - tn: 1803.1754 - fn: 182.4211 - accuracy: 0.7457 - precision: 0.4005 - recall: 0.6660 - auc: 0.7882 - prc: 0.5076 - val_loss: 0.5097 - val_tp: 225.0000 - val_fp: 245.0000 - val_tn: 838.0000 - val_fn: 92.0000 - val_accuracy: 0.7593 - val_precision: 0.4787 - val_recall: 0.7098 - val_auc: 0.8232 - val_prc: 0.6264
Epoch 64/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5317 - tp: 407.9474 - fp: 553.7018 - tn: 1768.5965 - fn: 168.0000 - accuracy: 0.7517 - precision: 0.4281 - recall: 0.7080 - auc: 0.8105 - prc: 0.5527 - val_loss: 0.5058 - val_tp: 221.0000 - val_fp: 235.0000 - val_tn: 848.0000 - val_fn: 96.0000 - val_accuracy: 0.7636 - val_precision: 0.4846 - val_recall: 0.6972 - val_auc: 0.8233 - val_prc: 0.6282
Epoch 65/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5277 - tp: 389.5263 - fp: 506.6316 - tn: 1821.2281 - fn: 180.8596 - accuracy: 0.7646 - precision: 0.4349 - recall: 0.6881 - auc: 0.8090 - prc: 0.5399 - val_loss: 0.5095 - val_tp: 227.0000 - val_fp: 246.0000 - val_tn: 837.0000 - val_fn: 90.0000 - val_accuracy: 0.7600 - val_precision: 0.4799 - val_recall: 0.7161 - val_auc: 0.8239 - val_prc: 0.6302
Epoch 66/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5297 - tp: 398.0526 - fp: 528.6140 - tn: 1806.5263 - fn: 165.0526 - accuracy: 0.7599 - precision: 0.4202 - recall: 0.7118 - auc: 0.8101 - prc: 0.5115 - val_loss: 0.5021 - val_tp: 220.0000 - val_fp: 229.0000 - val_tn: 854.0000 - val_fn: 97.0000 - val_accuracy: 0.7671 - val_precision: 0.4900 - val_recall: 0.6940 - val_auc: 0.8250 - val_prc: 0.6332
Epoch 67/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5318 - tp: 401.1754 - fp: 514.1228 - tn: 1812.1579 - fn: 170.7895 - accuracy: 0.7642 - precision: 0.4309 - recall: 0.7044 - auc: 0.8070 - prc: 0.5266 - val_loss: 0.5065 - val_tp: 222.0000 - val_fp: 238.0000 - val_tn: 845.0000 - val_fn: 95.0000 - val_accuracy: 0.7621 - val_precision: 0.4826 - val_recall: 0.7003 - val_auc: 0.8246 - val_prc: 0.6330
Epoch 68/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5347 - tp: 391.9825 - fp: 526.4211 - tn: 1795.7719 - fn: 184.0702 - accuracy: 0.7568 - precision: 0.4322 - recall: 0.6809 - auc: 0.8093 - prc: 0.5433 - val_loss: 0.5016 - val_tp: 218.0000 - val_fp: 230.0000 - val_tn: 853.0000 - val_fn: 99.0000 - val_accuracy: 0.7650 - val_precision: 0.4866 - val_recall: 0.6877 - val_auc: 0.8247 - val_prc: 0.6357
Epoch 69/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5292 - tp: 414.1053 - fp: 511.9123 - tn: 1799.3158 - fn: 172.9123 - accuracy: 0.7688 - precision: 0.4654 - recall: 0.7135 - auc: 0.8221 - prc: 0.5701 - val_loss: 0.4990 - val_tp: 218.0000 - val_fp: 230.0000 - val_tn: 853.0000 - val_fn: 99.0000 - val_accuracy: 0.7650 - val_precision: 0.4866 - val_recall: 0.6877 - val_auc: 0.8250 - val_prc: 0.6352
Epoch 70/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5301 - tp: 385.1579 - fp: 502.3860 - tn: 1825.9649 - fn: 184.7368 - accuracy: 0.7601 - precision: 0.4271 - recall: 0.6700 - auc: 0.8088 - prc: 0.5374 - val_loss: 0.5039 - val_tp: 221.0000 - val_fp: 231.0000 - val_tn: 852.0000 - val_fn: 96.0000 - val_accuracy: 0.7664 - val_precision: 0.4889 - val_recall: 0.6972 - val_auc: 0.8263 - val_prc: 0.6376
Epoch 71/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5412 - tp: 417.2456 - fp: 521.6316 - tn: 1780.6667 - fn: 178.7018 - accuracy: 0.7560 - precision: 0.4483 - recall: 0.7005 - auc: 0.8090 - prc: 0.5808 - val_loss: 0.5046 - val_tp: 221.0000 - val_fp: 234.0000 - val_tn: 849.0000 - val_fn: 96.0000 - val_accuracy: 0.7643 - val_precision: 0.4857 - val_recall: 0.6972 - val_auc: 0.8263 - val_prc: 0.6377
Epoch 72/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5541 - tp: 401.4211 - fp: 524.0877 - tn: 1791.3684 - fn: 181.3684 - accuracy: 0.7528 - precision: 0.4346 - recall: 0.6794 - auc: 0.7959 - prc: 0.5599 - val_loss: 0.5012 - val_tp: 219.0000 - val_fp: 232.0000 - val_tn: 851.0000 - val_fn: 98.0000 - val_accuracy: 0.7643 - val_precision: 0.4856 - val_recall: 0.6909 - val_auc: 0.8267 - val_prc: 0.6374
Epoch 73/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5475 - tp: 389.2281 - fp: 526.1579 - tn: 1795.7193 - fn: 187.1404 - accuracy: 0.7491 - precision: 0.4240 - recall: 0.6684 - auc: 0.7974 - prc: 0.5397 - val_loss: 0.5021 - val_tp: 220.0000 - val_fp: 231.0000 - val_tn: 852.0000 - val_fn: 97.0000 - val_accuracy: 0.7657 - val_precision: 0.4878 - val_recall: 0.6940 - val_auc: 0.8268 - val_prc: 0.6386
Epoch 74/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5091 - tp: 410.0000 - fp: 515.1579 - tn: 1805.1404 - fn: 167.9474 - accuracy: 0.7645 - precision: 0.4446 - recall: 0.7225 - auc: 0.8308 - prc: 0.5860 - val_loss: 0.5010 - val_tp: 220.0000 - val_fp: 230.0000 - val_tn: 853.0000 - val_fn: 97.0000 - val_accuracy: 0.7664 - val_precision: 0.4889 - val_recall: 0.6940 - val_auc: 0.8263 - val_prc: 0.6401
Epoch 75/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5296 - tp: 401.8421 - fp: 513.7895 - tn: 1808.3509 - fn: 174.2632 - accuracy: 0.7592 - precision: 0.4368 - recall: 0.6916 - auc: 0.8132 - prc: 0.5657 - val_loss: 0.5047 - val_tp: 222.0000 - val_fp: 237.0000 - val_tn: 846.0000 - val_fn: 95.0000 - val_accuracy: 0.7629 - val_precision: 0.4837 - val_recall: 0.7003 - val_auc: 0.8270 - val_prc: 0.6410
Epoch 76/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5160 - tp: 387.1754 - fp: 530.1579 - tn: 1804.1579 - fn: 176.7544 - accuracy: 0.7586 - precision: 0.4198 - recall: 0.6871 - auc: 0.8155 - prc: 0.5495 - val_loss: 0.5022 - val_tp: 222.0000 - val_fp: 232.0000 - val_tn: 851.0000 - val_fn: 95.0000 - val_accuracy: 0.7664 - val_precision: 0.4890 - val_recall: 0.7003 - val_auc: 0.8274 - val_prc: 0.6397
Epoch 77/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5233 - tp: 401.1404 - fp: 524.5789 - tn: 1800.4737 - fn: 172.0526 - accuracy: 0.7607 - precision: 0.4462 - recall: 0.6979 - auc: 0.8213 - prc: 0.5802 - val_loss: 0.4965 - val_tp: 221.0000 - val_fp: 224.0000 - val_tn: 859.0000 - val_fn: 96.0000 - val_accuracy: 0.7714 - val_precision: 0.4966 - val_recall: 0.6972 - val_auc: 0.8286 - val_prc: 0.6422
Epoch 78/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5200 - tp: 390.9123 - fp: 511.1754 - tn: 1810.8596 - fn: 185.2982 - accuracy: 0.7540 - precision: 0.4171 - recall: 0.6636 - auc: 0.8101 - prc: 0.5538 - val_loss: 0.4988 - val_tp: 222.0000 - val_fp: 229.0000 - val_tn: 854.0000 - val_fn: 95.0000 - val_accuracy: 0.7686 - val_precision: 0.4922 - val_recall: 0.7003 - val_auc: 0.8280 - val_prc: 0.6413
Epoch 79/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5252 - tp: 398.5614 - fp: 522.9649 - tn: 1805.5263 - fn: 171.1930 - accuracy: 0.7655 - precision: 0.4470 - recall: 0.7045 - auc: 0.8192 - prc: 0.5854 - val_loss: 0.4933 - val_tp: 219.0000 - val_fp: 221.0000 - val_tn: 862.0000 - val_fn: 98.0000 - val_accuracy: 0.7721 - val_precision: 0.4977 - val_recall: 0.6909 - val_auc: 0.8288 - val_prc: 0.6421
Epoch 80/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5165 - tp: 385.9298 - fp: 484.4386 - tn: 1841.2632 - fn: 186.6140 - accuracy: 0.7735 - precision: 0.4422 - recall: 0.6776 - auc: 0.8176 - prc: 0.5545 - val_loss: 0.4982 - val_tp: 222.0000 - val_fp: 227.0000 - val_tn: 856.0000 - val_fn: 95.0000 - val_accuracy: 0.7700 - val_precision: 0.4944 - val_recall: 0.7003 - val_auc: 0.8299 - val_prc: 0.6445
Epoch 81/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5266 - tp: 400.9474 - fp: 497.5614 - tn: 1823.2632 - fn: 176.4737 - accuracy: 0.7702 - precision: 0.4509 - recall: 0.6931 - auc: 0.8124 - prc: 0.5544 - val_loss: 0.4938 - val_tp: 220.0000 - val_fp: 224.0000 - val_tn: 859.0000 - val_fn: 97.0000 - val_accuracy: 0.7707 - val_precision: 0.4955 - val_recall: 0.6940 - val_auc: 0.8295 - val_prc: 0.6427
Epoch 82/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5017 - tp: 379.9474 - fp: 483.6842 - tn: 1865.7544 - fn: 168.8596 - accuracy: 0.7798 - precision: 0.4358 - recall: 0.7044 - auc: 0.8219 - prc: 0.5349 - val_loss: 0.4960 - val_tp: 222.0000 - val_fp: 230.0000 - val_tn: 853.0000 - val_fn: 95.0000 - val_accuracy: 0.7679 - val_precision: 0.4912 - val_recall: 0.7003 - val_auc: 0.8301 - val_prc: 0.6445
Epoch 83/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5212 - tp: 395.1579 - fp: 525.7368 - tn: 1802.1930 - fn: 175.1579 - accuracy: 0.7546 - precision: 0.4259 - recall: 0.6960 - auc: 0.8149 - prc: 0.5576 - val_loss: 0.4989 - val_tp: 223.0000 - val_fp: 234.0000 - val_tn: 849.0000 - val_fn: 94.0000 - val_accuracy: 0.7657 - val_precision: 0.4880 - val_recall: 0.7035 - val_auc: 0.8313 - val_prc: 0.6479
Epoch 84/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5204 - tp: 409.4035 - fp: 518.7895 - tn: 1799.1053 - fn: 170.9474 - accuracy: 0.7655 - precision: 0.4502 - recall: 0.7138 - auc: 0.8214 - prc: 0.5794 - val_loss: 0.4938 - val_tp: 221.0000 - val_fp: 226.0000 - val_tn: 857.0000 - val_fn: 96.0000 - val_accuracy: 0.7700 - val_precision: 0.4944 - val_recall: 0.6972 - val_auc: 0.8324 - val_prc: 0.6502
Epoch 85/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5207 - tp: 397.0702 - fp: 490.8772 - tn: 1835.1579 - fn: 175.1404 - accuracy: 0.7769 - precision: 0.4630 - recall: 0.6999 - auc: 0.8199 - prc: 0.5813 - val_loss: 0.4945 - val_tp: 223.0000 - val_fp: 227.0000 - val_tn: 856.0000 - val_fn: 94.0000 - val_accuracy: 0.7707 - val_precision: 0.4956 - val_recall: 0.7035 - val_auc: 0.8325 - val_prc: 0.6520
Epoch 86/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5162 - tp: 396.5965 - fp: 493.5439 - tn: 1833.1228 - fn: 174.9825 - accuracy: 0.7718 - precision: 0.4507 - recall: 0.6919 - auc: 0.8239 - prc: 0.5668 - val_loss: 0.4932 - val_tp: 223.0000 - val_fp: 224.0000 - val_tn: 859.0000 - val_fn: 94.0000 - val_accuracy: 0.7729 - val_precision: 0.4989 - val_recall: 0.7035 - val_auc: 0.8327 - val_prc: 0.6534
Epoch 87/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5025 - tp: 400.4737 - fp: 483.3860 - tn: 1846.4737 - fn: 167.9123 - accuracy: 0.7781 - precision: 0.4592 - recall: 0.7075 - auc: 0.8328 - prc: 0.5942 - val_loss: 0.4886 - val_tp: 221.0000 - val_fp: 215.0000 - val_tn: 868.0000 - val_fn: 96.0000 - val_accuracy: 0.7779 - val_precision: 0.5069 - val_recall: 0.6972 - val_auc: 0.8335 - val_prc: 0.6530
Epoch 88/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5329 - tp: 392.0351 - fp: 486.8421 - tn: 1833.0175 - fn: 186.3509 - accuracy: 0.7698 - precision: 0.4492 - recall: 0.6730 - auc: 0.8101 - prc: 0.5679 - val_loss: 0.4935 - val_tp: 224.0000 - val_fp: 228.0000 - val_tn: 855.0000 - val_fn: 93.0000 - val_accuracy: 0.7707 - val_precision: 0.4956 - val_recall: 0.7066 - val_auc: 0.8334 - val_prc: 0.6519
Epoch 89/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5126 - tp: 389.9123 - fp: 494.6842 - tn: 1837.5965 - fn: 176.0526 - accuracy: 0.7690 - precision: 0.4421 - recall: 0.6935 - auc: 0.8213 - prc: 0.5798 - val_loss: 0.4886 - val_tp: 224.0000 - val_fp: 221.0000 - val_tn: 862.0000 - val_fn: 93.0000 - val_accuracy: 0.7757 - val_precision: 0.5034 - val_recall: 0.7066 - val_auc: 0.8350 - val_prc: 0.6557
Epoch 90/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5149 - tp: 389.8246 - fp: 496.1228 - tn: 1837.0175 - fn: 175.2807 - accuracy: 0.7684 - precision: 0.4357 - recall: 0.6821 - auc: 0.8191 - prc: 0.5480 - val_loss: 0.4933 - val_tp: 225.0000 - val_fp: 232.0000 - val_tn: 851.0000 - val_fn: 92.0000 - val_accuracy: 0.7686 - val_precision: 0.4923 - val_recall: 0.7098 - val_auc: 0.8342 - val_prc: 0.6558
Epoch 91/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5039 - tp: 413.8070 - fp: 494.8772 - tn: 1826.5965 - fn: 162.9649 - accuracy: 0.7739 - precision: 0.4491 - recall: 0.7244 - auc: 0.8286 - prc: 0.5853 - val_loss: 0.4921 - val_tp: 225.0000 - val_fp: 229.0000 - val_tn: 854.0000 - val_fn: 92.0000 - val_accuracy: 0.7707 - val_precision: 0.4956 - val_recall: 0.7098 - val_auc: 0.8349 - val_prc: 0.6570
Epoch 92/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5267 - tp: 407.6667 - fp: 499.7544 - tn: 1820.5439 - fn: 170.2807 - accuracy: 0.7695 - precision: 0.4518 - recall: 0.7113 - auc: 0.8190 - prc: 0.5768 - val_loss: 0.4930 - val_tp: 225.0000 - val_fp: 228.0000 - val_tn: 855.0000 - val_fn: 92.0000 - val_accuracy: 0.7714 - val_precision: 0.4967 - val_recall: 0.7098 - val_auc: 0.8357 - val_prc: 0.6575
Epoch 93/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5212 - tp: 392.3684 - fp: 503.1053 - tn: 1826.2982 - fn: 176.4737 - accuracy: 0.7631 - precision: 0.4323 - recall: 0.6881 - auc: 0.8116 - prc: 0.5612 - val_loss: 0.4874 - val_tp: 223.0000 - val_fp: 221.0000 - val_tn: 862.0000 - val_fn: 94.0000 - val_accuracy: 0.7750 - val_precision: 0.5023 - val_recall: 0.7035 - val_auc: 0.8372 - val_prc: 0.6599
Epoch 94/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5444 - tp: 399.8246 - fp: 518.0175 - tn: 1803.5263 - fn: 176.8772 - accuracy: 0.7570 - precision: 0.4360 - recall: 0.6887 - auc: 0.8023 - prc: 0.5561 - val_loss: 0.4871 - val_tp: 223.0000 - val_fp: 217.0000 - val_tn: 866.0000 - val_fn: 94.0000 - val_accuracy: 0.7779 - val_precision: 0.5068 - val_recall: 0.7035 - val_auc: 0.8369 - val_prc: 0.6630
Epoch 95/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5334 - tp: 400.9298 - fp: 497.0351 - tn: 1810.9298 - fn: 189.3509 - accuracy: 0.7601 - precision: 0.4420 - recall: 0.6715 - auc: 0.8091 - prc: 0.5885 - val_loss: 0.4866 - val_tp: 223.0000 - val_fp: 220.0000 - val_tn: 863.0000 - val_fn: 94.0000 - val_accuracy: 0.7757 - val_precision: 0.5034 - val_recall: 0.7035 - val_auc: 0.8371 - val_prc: 0.6624
Epoch 96/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5261 - tp: 408.1404 - fp: 495.1754 - tn: 1819.0877 - fn: 175.8421 - accuracy: 0.7646 - precision: 0.4434 - recall: 0.6943 - auc: 0.8120 - prc: 0.5732 - val_loss: 0.4851 - val_tp: 223.0000 - val_fp: 217.0000 - val_tn: 866.0000 - val_fn: 94.0000 - val_accuracy: 0.7779 - val_precision: 0.5068 - val_recall: 0.7035 - val_auc: 0.8374 - val_prc: 0.6641
Epoch 97/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5341 - tp: 409.0526 - fp: 514.6140 - tn: 1801.1754 - fn: 173.4035 - accuracy: 0.7602 - precision: 0.4493 - recall: 0.7058 - auc: 0.8131 - prc: 0.5801 - val_loss: 0.4846 - val_tp: 225.0000 - val_fp: 221.0000 - val_tn: 862.0000 - val_fn: 92.0000 - val_accuracy: 0.7764 - val_precision: 0.5045 - val_recall: 0.7098 - val_auc: 0.8376 - val_prc: 0.6624
Epoch 98/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5118 - tp: 390.2456 - fp: 494.0351 - tn: 1834.2105 - fn: 179.7544 - accuracy: 0.7677 - precision: 0.4419 - recall: 0.6871 - auc: 0.8239 - prc: 0.5861 - val_loss: 0.4935 - val_tp: 228.0000 - val_fp: 230.0000 - val_tn: 853.0000 - val_fn: 89.0000 - val_accuracy: 0.7721 - val_precision: 0.4978 - val_recall: 0.7192 - val_auc: 0.8379 - val_prc: 0.6653
Epoch 99/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5161 - tp: 387.2982 - fp: 539.3158 - tn: 1798.4035 - fn: 173.2281 - accuracy: 0.7530 - precision: 0.4129 - recall: 0.6933 - auc: 0.8127 - prc: 0.5750 - val_loss: 0.4892 - val_tp: 226.0000 - val_fp: 226.0000 - val_tn: 857.0000 - val_fn: 91.0000 - val_accuracy: 0.7736 - val_precision: 0.5000 - val_recall: 0.7129 - val_auc: 0.8381 - val_prc: 0.6665
Epoch 100/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5219 - tp: 419.9649 - fp: 497.4211 - tn: 1808.9298 - fn: 171.9298 - accuracy: 0.7691 - precision: 0.4608 - recall: 0.7019 - auc: 0.8238 - prc: 0.5980 - val_loss: 0.4866 - val_tp: 224.0000 - val_fp: 219.0000 - val_tn: 864.0000 - val_fn: 93.0000 - val_accuracy: 0.7771 - val_precision: 0.5056 - val_recall: 0.7066 - val_auc: 0.8382 - val_prc: 0.6663
Epoch 101/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5088 - tp: 397.4912 - fp: 487.5439 - tn: 1843.7368 - fn: 169.4737 - accuracy: 0.7722 - precision: 0.4492 - recall: 0.7026 - auc: 0.8273 - prc: 0.5719 - val_loss: 0.4869 - val_tp: 226.0000 - val_fp: 222.0000 - val_tn: 861.0000 - val_fn: 91.0000 - val_accuracy: 0.7764 - val_precision: 0.5045 - val_recall: 0.7129 - val_auc: 0.8390 - val_prc: 0.6667
Epoch 102/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5042 - tp: 395.7368 - fp: 497.5263 - tn: 1834.1053 - fn: 170.8772 - accuracy: 0.7721 - precision: 0.4424 - recall: 0.7077 - auc: 0.8263 - prc: 0.5832 - val_loss: 0.4828 - val_tp: 222.0000 - val_fp: 211.0000 - val_tn: 872.0000 - val_fn: 95.0000 - val_accuracy: 0.7814 - val_precision: 0.5127 - val_recall: 0.7003 - val_auc: 0.8388 - val_prc: 0.6660
Epoch 103/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5036 - tp: 394.8947 - fp: 476.3860 - tn: 1849.3509 - fn: 177.6140 - accuracy: 0.7741 - precision: 0.4476 - recall: 0.6904 - auc: 0.8265 - prc: 0.5916 - val_loss: 0.4847 - val_tp: 224.0000 - val_fp: 219.0000 - val_tn: 864.0000 - val_fn: 93.0000 - val_accuracy: 0.7771 - val_precision: 0.5056 - val_recall: 0.7066 - val_auc: 0.8381 - val_prc: 0.6658
Epoch 104/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5226 - tp: 391.2632 - fp: 485.9825 - tn: 1837.0526 - fn: 183.9474 - accuracy: 0.7688 - precision: 0.4414 - recall: 0.6794 - auc: 0.8136 - prc: 0.5624 - val_loss: 0.4856 - val_tp: 226.0000 - val_fp: 223.0000 - val_tn: 860.0000 - val_fn: 91.0000 - val_accuracy: 0.7757 - val_precision: 0.5033 - val_recall: 0.7129 - val_auc: 0.8385 - val_prc: 0.6658
Epoch 105/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5310 - tp: 389.1228 - fp: 501.1754 - tn: 1826.9298 - fn: 181.0175 - accuracy: 0.7624 - precision: 0.4307 - recall: 0.6767 - auc: 0.8061 - prc: 0.5470 - val_loss: 0.4844 - val_tp: 226.0000 - val_fp: 220.0000 - val_tn: 863.0000 - val_fn: 91.0000 - val_accuracy: 0.7779 - val_precision: 0.5067 - val_recall: 0.7129 - val_auc: 0.8398 - val_prc: 0.6699
Epoch 106/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5184 - tp: 393.8070 - fp: 492.5965 - tn: 1829.5965 - fn: 182.2456 - accuracy: 0.7705 - precision: 0.4540 - recall: 0.6755 - auc: 0.8214 - prc: 0.5949 - val_loss: 0.4823 - val_tp: 223.0000 - val_fp: 218.0000 - val_tn: 865.0000 - val_fn: 94.0000 - val_accuracy: 0.7771 - val_precision: 0.5057 - val_recall: 0.7035 - val_auc: 0.8398 - val_prc: 0.6696
Epoch 107/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5322 - tp: 399.7719 - fp: 498.4386 - tn: 1822.8246 - fn: 177.2105 - accuracy: 0.7670 - precision: 0.4462 - recall: 0.6917 - auc: 0.8094 - prc: 0.5662 - val_loss: 0.4847 - val_tp: 229.0000 - val_fp: 223.0000 - val_tn: 860.0000 - val_fn: 88.0000 - val_accuracy: 0.7779 - val_precision: 0.5066 - val_recall: 0.7224 - val_auc: 0.8403 - val_prc: 0.6698
Epoch 108/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5254 - tp: 388.6140 - fp: 504.7368 - tn: 1830.2105 - fn: 174.6842 - accuracy: 0.7584 - precision: 0.4215 - recall: 0.6807 - auc: 0.8073 - prc: 0.5530 - val_loss: 0.4831 - val_tp: 227.0000 - val_fp: 218.0000 - val_tn: 865.0000 - val_fn: 90.0000 - val_accuracy: 0.7800 - val_precision: 0.5101 - val_recall: 0.7161 - val_auc: 0.8408 - val_prc: 0.6700
Epoch 109/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5175 - tp: 403.9825 - fp: 476.3509 - tn: 1838.7018 - fn: 179.2105 - accuracy: 0.7762 - precision: 0.4676 - recall: 0.6942 - auc: 0.8244 - prc: 0.5931 - val_loss: 0.4819 - val_tp: 225.0000 - val_fp: 214.0000 - val_tn: 869.0000 - val_fn: 92.0000 - val_accuracy: 0.7814 - val_precision: 0.5125 - val_recall: 0.7098 - val_auc: 0.8410 - val_prc: 0.6705
Epoch 110/200
56/56 [==============================] - 0s 2ms/step - loss: 0.4987 - tp: 386.7719 - fp: 458.3333 - tn: 1871.8246 - fn: 181.3158 - accuracy: 0.7825 - precision: 0.4586 - recall: 0.6885 - auc: 0.8330 - prc: 0.6026 - val_loss: 0.4840 - val_tp: 228.0000 - val_fp: 217.0000 - val_tn: 866.0000 - val_fn: 89.0000 - val_accuracy: 0.7814 - val_precision: 0.5124 - val_recall: 0.7192 - val_auc: 0.8405 - val_prc: 0.6713
Epoch 111/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5136 - tp: 402.2105 - fp: 506.9298 - tn: 1818.6667 - fn: 170.4386 - accuracy: 0.7646 - precision: 0.4458 - recall: 0.7048 - auc: 0.8260 - prc: 0.5906 - val_loss: 0.4785 - val_tp: 223.0000 - val_fp: 208.0000 - val_tn: 875.0000 - val_fn: 94.0000 - val_accuracy: 0.7843 - val_precision: 0.5174 - val_recall: 0.7035 - val_auc: 0.8407 - val_prc: 0.6710
Epoch 112/200
56/56 [==============================] - 0s 2ms/step - loss: 0.4928 - tp: 405.6491 - fp: 461.1754 - tn: 1863.6842 - fn: 167.7368 - accuracy: 0.7815 - precision: 0.4660 - recall: 0.7125 - auc: 0.8399 - prc: 0.6279 - val_loss: 0.4801 - val_tp: 226.0000 - val_fp: 214.0000 - val_tn: 869.0000 - val_fn: 91.0000 - val_accuracy: 0.7821 - val_precision: 0.5136 - val_recall: 0.7129 - val_auc: 0.8408 - val_prc: 0.6712
Epoch 113/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5165 - tp: 398.2632 - fp: 474.9123 - tn: 1858.7193 - fn: 166.3509 - accuracy: 0.7777 - precision: 0.4507 - recall: 0.6998 - auc: 0.8158 - prc: 0.5846 - val_loss: 0.4854 - val_tp: 231.0000 - val_fp: 222.0000 - val_tn: 861.0000 - val_fn: 86.0000 - val_accuracy: 0.7800 - val_precision: 0.5099 - val_recall: 0.7287 - val_auc: 0.8404 - val_prc: 0.6702
Epoch 114/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5368 - tp: 407.1754 - fp: 491.8772 - tn: 1819.0175 - fn: 180.1754 - accuracy: 0.7685 - precision: 0.4609 - recall: 0.6935 - auc: 0.8115 - prc: 0.5818 - val_loss: 0.4858 - val_tp: 228.0000 - val_fp: 223.0000 - val_tn: 860.0000 - val_fn: 89.0000 - val_accuracy: 0.7771 - val_precision: 0.5055 - val_recall: 0.7192 - val_auc: 0.8401 - val_prc: 0.6703
Epoch 115/200
56/56 [==============================] - 0s 2ms/step - loss: 0.4977 - tp: 389.9649 - fp: 483.0000 - tn: 1858.0877 - fn: 167.1930 - accuracy: 0.7782 - precision: 0.4454 - recall: 0.7118 - auc: 0.8287 - prc: 0.5790 - val_loss: 0.4822 - val_tp: 225.0000 - val_fp: 218.0000 - val_tn: 865.0000 - val_fn: 92.0000 - val_accuracy: 0.7786 - val_precision: 0.5079 - val_recall: 0.7098 - val_auc: 0.8407 - val_prc: 0.6729
Epoch 116/200
56/56 [==============================] - 0s 2ms/step - loss: 0.4921 - tp: 394.5965 - fp: 488.5789 - tn: 1853.2632 - fn: 161.8070 - accuracy: 0.7757 - precision: 0.4386 - recall: 0.7098 - auc: 0.8301 - prc: 0.6081 - val_loss: 0.4860 - val_tp: 228.0000 - val_fp: 223.0000 - val_tn: 860.0000 - val_fn: 89.0000 - val_accuracy: 0.7771 - val_precision: 0.5055 - val_recall: 0.7192 - val_auc: 0.8405 - val_prc: 0.6721
Epoch 117/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5096 - tp: 389.1228 - fp: 481.1754 - tn: 1860.5088 - fn: 167.4386 - accuracy: 0.7790 - precision: 0.4478 - recall: 0.7096 - auc: 0.8212 - prc: 0.5782 - val_loss: 0.4841 - val_tp: 226.0000 - val_fp: 219.0000 - val_tn: 864.0000 - val_fn: 91.0000 - val_accuracy: 0.7786 - val_precision: 0.5079 - val_recall: 0.7129 - val_auc: 0.8415 - val_prc: 0.6743
Epoch 118/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5218 - tp: 392.5789 - fp: 501.0877 - tn: 1825.2982 - fn: 179.2807 - accuracy: 0.7608 - precision: 0.4330 - recall: 0.6855 - auc: 0.8137 - prc: 0.5707 - val_loss: 0.4837 - val_tp: 227.0000 - val_fp: 222.0000 - val_tn: 861.0000 - val_fn: 90.0000 - val_accuracy: 0.7771 - val_precision: 0.5056 - val_recall: 0.7161 - val_auc: 0.8409 - val_prc: 0.6723
Epoch 119/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5121 - tp: 403.5789 - fp: 481.4211 - tn: 1845.2105 - fn: 168.0351 - accuracy: 0.7766 - precision: 0.4539 - recall: 0.7163 - auc: 0.8244 - prc: 0.5733 - val_loss: 0.4828 - val_tp: 224.0000 - val_fp: 221.0000 - val_tn: 862.0000 - val_fn: 93.0000 - val_accuracy: 0.7757 - val_precision: 0.5034 - val_recall: 0.7066 - val_auc: 0.8406 - val_prc: 0.6718
Epoch 120/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5222 - tp: 391.9825 - fp: 486.5965 - tn: 1837.6842 - fn: 181.9825 - accuracy: 0.7703 - precision: 0.4457 - recall: 0.6919 - auc: 0.8182 - prc: 0.5732 - val_loss: 0.4814 - val_tp: 223.0000 - val_fp: 218.0000 - val_tn: 865.0000 - val_fn: 94.0000 - val_accuracy: 0.7771 - val_precision: 0.5057 - val_recall: 0.7035 - val_auc: 0.8412 - val_prc: 0.6733
Epoch 121/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5148 - tp: 407.0877 - fp: 472.3509 - tn: 1842.4386 - fn: 176.3684 - accuracy: 0.7750 - precision: 0.4615 - recall: 0.7037 - auc: 0.8225 - prc: 0.5882 - val_loss: 0.4830 - val_tp: 224.0000 - val_fp: 223.0000 - val_tn: 860.0000 - val_fn: 93.0000 - val_accuracy: 0.7743 - val_precision: 0.5011 - val_recall: 0.7066 - val_auc: 0.8408 - val_prc: 0.6720
Epoch 122/200
56/56 [==============================] - 0s 2ms/step - loss: 0.4962 - tp: 403.2807 - fp: 476.7544 - tn: 1849.6842 - fn: 168.5263 - accuracy: 0.7796 - precision: 0.4527 - recall: 0.7090 - auc: 0.8366 - prc: 0.5790 - val_loss: 0.4738 - val_tp: 221.0000 - val_fp: 207.0000 - val_tn: 876.0000 - val_fn: 96.0000 - val_accuracy: 0.7836 - val_precision: 0.5164 - val_recall: 0.6972 - val_auc: 0.8411 - val_prc: 0.6729
Epoch 123/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5186 - tp: 395.2281 - fp: 465.2456 - tn: 1851.3860 - fn: 186.3860 - accuracy: 0.7758 - precision: 0.4589 - recall: 0.6862 - auc: 0.8234 - prc: 0.5661 - val_loss: 0.4811 - val_tp: 225.0000 - val_fp: 219.0000 - val_tn: 864.0000 - val_fn: 92.0000 - val_accuracy: 0.7779 - val_precision: 0.5068 - val_recall: 0.7098 - val_auc: 0.8408 - val_prc: 0.6735
Epoch 124/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5108 - tp: 415.7719 - fp: 462.9123 - tn: 1844.0351 - fn: 175.5263 - accuracy: 0.7814 - precision: 0.4862 - recall: 0.7099 - auc: 0.8331 - prc: 0.6329 - val_loss: 0.4801 - val_tp: 223.0000 - val_fp: 218.0000 - val_tn: 865.0000 - val_fn: 94.0000 - val_accuracy: 0.7771 - val_precision: 0.5057 - val_recall: 0.7035 - val_auc: 0.8410 - val_prc: 0.6743
Epoch 125/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5252 - tp: 396.9123 - fp: 458.8246 - tn: 1861.5965 - fn: 180.9123 - accuracy: 0.7808 - precision: 0.4658 - recall: 0.6836 - auc: 0.8162 - prc: 0.5849 - val_loss: 0.4819 - val_tp: 228.0000 - val_fp: 222.0000 - val_tn: 861.0000 - val_fn: 89.0000 - val_accuracy: 0.7779 - val_precision: 0.5067 - val_recall: 0.7192 - val_auc: 0.8415 - val_prc: 0.6753
Epoch 126/200
56/56 [==============================] - 0s 2ms/step - loss: 0.4886 - tp: 390.9825 - fp: 478.3684 - tn: 1861.2982 - fn: 167.5965 - accuracy: 0.7825 - precision: 0.4494 - recall: 0.7191 - auc: 0.8338 - prc: 0.6078 - val_loss: 0.4827 - val_tp: 228.0000 - val_fp: 219.0000 - val_tn: 864.0000 - val_fn: 89.0000 - val_accuracy: 0.7800 - val_precision: 0.5101 - val_recall: 0.7192 - val_auc: 0.8422 - val_prc: 0.6774
Epoch 127/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5236 - tp: 408.1228 - fp: 479.4737 - tn: 1829.8772 - fn: 180.7719 - accuracy: 0.7738 - precision: 0.4702 - recall: 0.6945 - auc: 0.8223 - prc: 0.5996 - val_loss: 0.4814 - val_tp: 228.0000 - val_fp: 224.0000 - val_tn: 859.0000 - val_fn: 89.0000 - val_accuracy: 0.7764 - val_precision: 0.5044 - val_recall: 0.7192 - val_auc: 0.8408 - val_prc: 0.6746
Epoch 128/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5010 - tp: 414.2105 - fp: 491.9825 - tn: 1840.1053 - fn: 151.9474 - accuracy: 0.7773 - precision: 0.4604 - recall: 0.7336 - auc: 0.8339 - prc: 0.5949 - val_loss: 0.4782 - val_tp: 226.0000 - val_fp: 220.0000 - val_tn: 863.0000 - val_fn: 91.0000 - val_accuracy: 0.7779 - val_precision: 0.5067 - val_recall: 0.7129 - val_auc: 0.8417 - val_prc: 0.6765
Epoch 129/200
56/56 [==============================] - 0s 2ms/step - loss: 0.4996 - tp: 390.2281 - fp: 465.4561 - tn: 1870.0175 - fn: 172.5439 - accuracy: 0.7835 - precision: 0.4538 - recall: 0.7004 - auc: 0.8250 - prc: 0.5935 - val_loss: 0.4774 - val_tp: 227.0000 - val_fp: 219.0000 - val_tn: 864.0000 - val_fn: 90.0000 - val_accuracy: 0.7793 - val_precision: 0.5090 - val_recall: 0.7161 - val_auc: 0.8420 - val_prc: 0.6774
Epoch 130/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5078 - tp: 402.3333 - fp: 471.0526 - tn: 1855.3333 - fn: 169.5263 - accuracy: 0.7800 - precision: 0.4623 - recall: 0.7129 - auc: 0.8303 - prc: 0.5838 - val_loss: 0.4792 - val_tp: 227.0000 - val_fp: 223.0000 - val_tn: 860.0000 - val_fn: 90.0000 - val_accuracy: 0.7764 - val_precision: 0.5044 - val_recall: 0.7161 - val_auc: 0.8419 - val_prc: 0.6770
Epoch 131/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5147 - tp: 393.0702 - fp: 509.7018 - tn: 1810.1228 - fn: 185.3509 - accuracy: 0.7580 - precision: 0.4360 - recall: 0.6766 - auc: 0.8233 - prc: 0.6014 - val_loss: 0.4811 - val_tp: 228.0000 - val_fp: 223.0000 - val_tn: 860.0000 - val_fn: 89.0000 - val_accuracy: 0.7771 - val_precision: 0.5055 - val_recall: 0.7192 - val_auc: 0.8410 - val_prc: 0.6756
Epoch 132/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5071 - tp: 397.5088 - fp: 466.7544 - tn: 1856.5965 - fn: 177.3860 - accuracy: 0.7802 - precision: 0.4651 - recall: 0.6951 - auc: 0.8311 - prc: 0.5936 - val_loss: 0.4786 - val_tp: 226.0000 - val_fp: 219.0000 - val_tn: 864.0000 - val_fn: 91.0000 - val_accuracy: 0.7786 - val_precision: 0.5079 - val_recall: 0.7129 - val_auc: 0.8422 - val_prc: 0.6783
Epoch 133/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5295 - tp: 412.8070 - fp: 485.9298 - tn: 1830.1053 - fn: 169.4035 - accuracy: 0.7735 - precision: 0.4585 - recall: 0.6928 - auc: 0.8201 - prc: 0.5764 - val_loss: 0.4792 - val_tp: 227.0000 - val_fp: 220.0000 - val_tn: 863.0000 - val_fn: 90.0000 - val_accuracy: 0.7786 - val_precision: 0.5078 - val_recall: 0.7161 - val_auc: 0.8419 - val_prc: 0.6771
Epoch 134/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5000 - tp: 402.1579 - fp: 479.4737 - tn: 1848.0175 - fn: 168.5965 - accuracy: 0.7802 - precision: 0.4608 - recall: 0.7089 - auc: 0.8359 - prc: 0.6007 - val_loss: 0.4781 - val_tp: 226.0000 - val_fp: 220.0000 - val_tn: 863.0000 - val_fn: 91.0000 - val_accuracy: 0.7779 - val_precision: 0.5067 - val_recall: 0.7129 - val_auc: 0.8422 - val_prc: 0.6781
Epoch 135/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5022 - tp: 412.4912 - fp: 474.4386 - tn: 1850.5439 - fn: 160.7719 - accuracy: 0.7839 - precision: 0.4645 - recall: 0.7183 - auc: 0.8301 - prc: 0.6033 - val_loss: 0.4828 - val_tp: 229.0000 - val_fp: 227.0000 - val_tn: 856.0000 - val_fn: 88.0000 - val_accuracy: 0.7750 - val_precision: 0.5022 - val_recall: 0.7224 - val_auc: 0.8425 - val_prc: 0.6793
Epoch 136/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5153 - tp: 407.3860 - fp: 484.4386 - tn: 1832.9123 - fn: 173.5088 - accuracy: 0.7735 - precision: 0.4550 - recall: 0.6978 - auc: 0.8192 - prc: 0.5987 - val_loss: 0.4782 - val_tp: 227.0000 - val_fp: 218.0000 - val_tn: 865.0000 - val_fn: 90.0000 - val_accuracy: 0.7800 - val_precision: 0.5101 - val_recall: 0.7161 - val_auc: 0.8432 - val_prc: 0.6800
Epoch 137/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5092 - tp: 398.3684 - fp: 462.9825 - tn: 1859.3158 - fn: 177.5789 - accuracy: 0.7802 - precision: 0.4675 - recall: 0.6961 - auc: 0.8277 - prc: 0.6114 - val_loss: 0.4769 - val_tp: 224.0000 - val_fp: 211.0000 - val_tn: 872.0000 - val_fn: 93.0000 - val_accuracy: 0.7829 - val_precision: 0.5149 - val_recall: 0.7066 - val_auc: 0.8433 - val_prc: 0.6802
Epoch 138/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5066 - tp: 390.8070 - fp: 479.6316 - tn: 1851.1053 - fn: 176.7018 - accuracy: 0.7732 - precision: 0.4487 - recall: 0.6885 - auc: 0.8279 - prc: 0.5903 - val_loss: 0.4780 - val_tp: 227.0000 - val_fp: 213.0000 - val_tn: 870.0000 - val_fn: 90.0000 - val_accuracy: 0.7836 - val_precision: 0.5159 - val_recall: 0.7161 - val_auc: 0.8439 - val_prc: 0.6810
Epoch 139/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5021 - tp: 383.1404 - fp: 473.7719 - tn: 1861.7368 - fn: 179.5965 - accuracy: 0.7734 - precision: 0.4386 - recall: 0.6773 - auc: 0.8246 - prc: 0.5720 - val_loss: 0.4769 - val_tp: 227.0000 - val_fp: 208.0000 - val_tn: 875.0000 - val_fn: 90.0000 - val_accuracy: 0.7871 - val_precision: 0.5218 - val_recall: 0.7161 - val_auc: 0.8442 - val_prc: 0.6827
Epoch 140/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5157 - tp: 393.5965 - fp: 495.2807 - tn: 1830.4912 - fn: 178.8772 - accuracy: 0.7637 - precision: 0.4376 - recall: 0.6922 - auc: 0.8185 - prc: 0.5889 - val_loss: 0.4795 - val_tp: 226.0000 - val_fp: 216.0000 - val_tn: 867.0000 - val_fn: 91.0000 - val_accuracy: 0.7807 - val_precision: 0.5113 - val_recall: 0.7129 - val_auc: 0.8434 - val_prc: 0.6804
Epoch 141/200
56/56 [==============================] - 0s 2ms/step - loss: 0.4958 - tp: 398.0175 - fp: 461.8421 - tn: 1868.8947 - fn: 169.4912 - accuracy: 0.7829 - precision: 0.4651 - recall: 0.7001 - auc: 0.8317 - prc: 0.6179 - val_loss: 0.4753 - val_tp: 224.0000 - val_fp: 213.0000 - val_tn: 870.0000 - val_fn: 93.0000 - val_accuracy: 0.7814 - val_precision: 0.5126 - val_recall: 0.7066 - val_auc: 0.8431 - val_prc: 0.6797
Epoch 142/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5101 - tp: 401.1930 - fp: 454.6491 - tn: 1874.5088 - fn: 167.8947 - accuracy: 0.7852 - precision: 0.4656 - recall: 0.7008 - auc: 0.8255 - prc: 0.5972 - val_loss: 0.4772 - val_tp: 226.0000 - val_fp: 212.0000 - val_tn: 871.0000 - val_fn: 91.0000 - val_accuracy: 0.7836 - val_precision: 0.5160 - val_recall: 0.7129 - val_auc: 0.8433 - val_prc: 0.6808
Epoch 143/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5077 - tp: 400.2982 - fp: 459.6491 - tn: 1859.9649 - fn: 178.3333 - accuracy: 0.7841 - precision: 0.4781 - recall: 0.6908 - auc: 0.8317 - prc: 0.6200 - val_loss: 0.4757 - val_tp: 225.0000 - val_fp: 216.0000 - val_tn: 867.0000 - val_fn: 92.0000 - val_accuracy: 0.7800 - val_precision: 0.5102 - val_recall: 0.7098 - val_auc: 0.8433 - val_prc: 0.6805
Epoch 144/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5079 - tp: 407.1053 - fp: 454.7368 - tn: 1871.2982 - fn: 165.1053 - accuracy: 0.7862 - precision: 0.4717 - recall: 0.7105 - auc: 0.8277 - prc: 0.6027 - val_loss: 0.4793 - val_tp: 227.0000 - val_fp: 219.0000 - val_tn: 864.0000 - val_fn: 90.0000 - val_accuracy: 0.7793 - val_precision: 0.5090 - val_recall: 0.7161 - val_auc: 0.8435 - val_prc: 0.6809
Epoch 145/200
56/56 [==============================] - 0s 2ms/step - loss: 0.4931 - tp: 396.1228 - fp: 460.3158 - tn: 1876.3860 - fn: 165.4211 - accuracy: 0.7885 - precision: 0.4678 - recall: 0.7015 - auc: 0.8346 - prc: 0.6138 - val_loss: 0.4795 - val_tp: 228.0000 - val_fp: 222.0000 - val_tn: 861.0000 - val_fn: 89.0000 - val_accuracy: 0.7779 - val_precision: 0.5067 - val_recall: 0.7192 - val_auc: 0.8434 - val_prc: 0.6802
Epoch 146/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5083 - tp: 387.8947 - fp: 466.5965 - tn: 1862.0351 - fn: 181.7193 - accuracy: 0.7772 - precision: 0.4431 - recall: 0.6731 - auc: 0.8212 - prc: 0.5819 - val_loss: 0.4818 - val_tp: 229.0000 - val_fp: 219.0000 - val_tn: 864.0000 - val_fn: 88.0000 - val_accuracy: 0.7807 - val_precision: 0.5112 - val_recall: 0.7224 - val_auc: 0.8436 - val_prc: 0.6810
Epoch 147/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5263 - tp: 416.2632 - fp: 508.0175 - tn: 1802.1228 - fn: 171.8421 - accuracy: 0.7670 - precision: 0.4520 - recall: 0.7144 - auc: 0.8198 - prc: 0.5771 - val_loss: 0.4811 - val_tp: 227.0000 - val_fp: 225.0000 - val_tn: 858.0000 - val_fn: 90.0000 - val_accuracy: 0.7750 - val_precision: 0.5022 - val_recall: 0.7161 - val_auc: 0.8430 - val_prc: 0.6792
Epoch 148/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5058 - tp: 412.6140 - fp: 459.2105 - tn: 1859.6491 - fn: 166.7719 - accuracy: 0.7861 - precision: 0.4779 - recall: 0.7251 - auc: 0.8357 - prc: 0.6073 - val_loss: 0.4749 - val_tp: 222.0000 - val_fp: 211.0000 - val_tn: 872.0000 - val_fn: 95.0000 - val_accuracy: 0.7814 - val_precision: 0.5127 - val_recall: 0.7003 - val_auc: 0.8435 - val_prc: 0.6807
Epoch 149/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5094 - tp: 396.6140 - fp: 468.4561 - tn: 1852.2456 - fn: 180.9298 - accuracy: 0.7751 - precision: 0.4592 - recall: 0.6861 - auc: 0.8249 - prc: 0.6106 - val_loss: 0.4782 - val_tp: 222.0000 - val_fp: 217.0000 - val_tn: 866.0000 - val_fn: 95.0000 - val_accuracy: 0.7771 - val_precision: 0.5057 - val_recall: 0.7003 - val_auc: 0.8433 - val_prc: 0.6801
Epoch 150/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5017 - tp: 392.5789 - fp: 486.1754 - tn: 1843.1754 - fn: 176.3158 - accuracy: 0.7703 - precision: 0.4365 - recall: 0.7015 - auc: 0.8273 - prc: 0.5731 - val_loss: 0.4809 - val_tp: 227.0000 - val_fp: 227.0000 - val_tn: 856.0000 - val_fn: 90.0000 - val_accuracy: 0.7736 - val_precision: 0.5000 - val_recall: 0.7161 - val_auc: 0.8423 - val_prc: 0.6790
Epoch 151/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5065 - tp: 406.3684 - fp: 472.3860 - tn: 1846.2807 - fn: 173.2105 - accuracy: 0.7782 - precision: 0.4603 - recall: 0.7030 - auc: 0.8315 - prc: 0.5930 - val_loss: 0.4761 - val_tp: 225.0000 - val_fp: 219.0000 - val_tn: 864.0000 - val_fn: 92.0000 - val_accuracy: 0.7779 - val_precision: 0.5068 - val_recall: 0.7098 - val_auc: 0.8428 - val_prc: 0.6796
Epoch 152/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5294 - tp: 400.7544 - fp: 464.2105 - tn: 1847.8246 - fn: 185.4561 - accuracy: 0.7737 - precision: 0.4657 - recall: 0.6760 - auc: 0.8166 - prc: 0.5841 - val_loss: 0.4770 - val_tp: 226.0000 - val_fp: 214.0000 - val_tn: 869.0000 - val_fn: 91.0000 - val_accuracy: 0.7821 - val_precision: 0.5136 - val_recall: 0.7129 - val_auc: 0.8432 - val_prc: 0.6804
Epoch 153/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5126 - tp: 390.8772 - fp: 471.6316 - tn: 1862.8596 - fn: 172.8772 - accuracy: 0.7754 - precision: 0.4526 - recall: 0.6928 - auc: 0.8230 - prc: 0.5856 - val_loss: 0.4777 - val_tp: 227.0000 - val_fp: 218.0000 - val_tn: 865.0000 - val_fn: 90.0000 - val_accuracy: 0.7800 - val_precision: 0.5101 - val_recall: 0.7161 - val_auc: 0.8430 - val_prc: 0.6811
Epoch 154/200
56/56 [==============================] - 0s 2ms/step - loss: 0.4870 - tp: 403.7368 - fp: 477.1228 - tn: 1859.2456 - fn: 158.1404 - accuracy: 0.7830 - precision: 0.4499 - recall: 0.7294 - auc: 0.8412 - prc: 0.5961 - val_loss: 0.4802 - val_tp: 228.0000 - val_fp: 223.0000 - val_tn: 860.0000 - val_fn: 89.0000 - val_accuracy: 0.7771 - val_precision: 0.5055 - val_recall: 0.7192 - val_auc: 0.8436 - val_prc: 0.6818
Epoch 155/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5104 - tp: 403.2105 - fp: 454.7544 - tn: 1869.1053 - fn: 171.1754 - accuracy: 0.7821 - precision: 0.4636 - recall: 0.6938 - auc: 0.8275 - prc: 0.5996 - val_loss: 0.4778 - val_tp: 226.0000 - val_fp: 218.0000 - val_tn: 865.0000 - val_fn: 91.0000 - val_accuracy: 0.7793 - val_precision: 0.5090 - val_recall: 0.7129 - val_auc: 0.8436 - val_prc: 0.6813
Epoch 156/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5137 - tp: 394.5088 - fp: 475.0175 - tn: 1844.8070 - fn: 183.9123 - accuracy: 0.7715 - precision: 0.4490 - recall: 0.6746 - auc: 0.8220 - prc: 0.5871 - val_loss: 0.4771 - val_tp: 227.0000 - val_fp: 213.0000 - val_tn: 870.0000 - val_fn: 90.0000 - val_accuracy: 0.7836 - val_precision: 0.5159 - val_recall: 0.7161 - val_auc: 0.8442 - val_prc: 0.6825
Epoch 157/200
56/56 [==============================] - 0s 2ms/step - loss: 0.4989 - tp: 411.1404 - fp: 470.5965 - tn: 1853.8596 - fn: 162.6491 - accuracy: 0.7781 - precision: 0.4613 - recall: 0.7251 - auc: 0.8363 - prc: 0.6100 - val_loss: 0.4739 - val_tp: 226.0000 - val_fp: 208.0000 - val_tn: 875.0000 - val_fn: 91.0000 - val_accuracy: 0.7864 - val_precision: 0.5207 - val_recall: 0.7129 - val_auc: 0.8441 - val_prc: 0.6818
Epoch 158/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5022 - tp: 394.1579 - fp: 474.5614 - tn: 1860.4737 - fn: 169.0526 - accuracy: 0.7732 - precision: 0.4336 - recall: 0.6902 - auc: 0.8204 - prc: 0.5915 - val_loss: 0.4773 - val_tp: 229.0000 - val_fp: 215.0000 - val_tn: 868.0000 - val_fn: 88.0000 - val_accuracy: 0.7836 - val_precision: 0.5158 - val_recall: 0.7224 - val_auc: 0.8438 - val_prc: 0.6821
Epoch 159/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5093 - tp: 408.7193 - fp: 449.9298 - tn: 1869.8421 - fn: 169.7544 - accuracy: 0.7841 - precision: 0.4704 - recall: 0.6974 - auc: 0.8268 - prc: 0.6059 - val_loss: 0.4751 - val_tp: 226.0000 - val_fp: 212.0000 - val_tn: 871.0000 - val_fn: 91.0000 - val_accuracy: 0.7836 - val_precision: 0.5160 - val_recall: 0.7129 - val_auc: 0.8436 - val_prc: 0.6812
Epoch 160/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5093 - tp: 401.0877 - fp: 453.3684 - tn: 1866.4211 - fn: 177.3684 - accuracy: 0.7829 - precision: 0.4702 - recall: 0.6928 - auc: 0.8270 - prc: 0.6064 - val_loss: 0.4758 - val_tp: 227.0000 - val_fp: 217.0000 - val_tn: 866.0000 - val_fn: 90.0000 - val_accuracy: 0.7807 - val_precision: 0.5113 - val_recall: 0.7161 - val_auc: 0.8430 - val_prc: 0.6802
Epoch 161/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5059 - tp: 399.3509 - fp: 456.8070 - tn: 1867.4035 - fn: 174.6842 - accuracy: 0.7807 - precision: 0.4613 - recall: 0.6963 - auc: 0.8279 - prc: 0.5962 - val_loss: 0.4752 - val_tp: 227.0000 - val_fp: 214.0000 - val_tn: 869.0000 - val_fn: 90.0000 - val_accuracy: 0.7829 - val_precision: 0.5147 - val_recall: 0.7161 - val_auc: 0.8426 - val_prc: 0.6790
Epoch 162/200
56/56 [==============================] - 0s 2ms/step - loss: 0.4883 - tp: 394.3333 - fp: 445.1930 - tn: 1889.1404 - fn: 169.5789 - accuracy: 0.7885 - precision: 0.4740 - recall: 0.7059 - auc: 0.8401 - prc: 0.6279 - val_loss: 0.4751 - val_tp: 227.0000 - val_fp: 216.0000 - val_tn: 867.0000 - val_fn: 90.0000 - val_accuracy: 0.7814 - val_precision: 0.5124 - val_recall: 0.7161 - val_auc: 0.8420 - val_prc: 0.6785
Epoch 163/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5059 - tp: 409.2456 - fp: 487.3158 - tn: 1828.7018 - fn: 172.9825 - accuracy: 0.7679 - precision: 0.4579 - recall: 0.7126 - auc: 0.8349 - prc: 0.6089 - val_loss: 0.4739 - val_tp: 225.0000 - val_fp: 210.0000 - val_tn: 873.0000 - val_fn: 92.0000 - val_accuracy: 0.7843 - val_precision: 0.5172 - val_recall: 0.7098 - val_auc: 0.8428 - val_prc: 0.6800
Epoch 164/200
56/56 [==============================] - 0s 2ms/step - loss: 0.4985 - tp: 385.2281 - fp: 453.9123 - tn: 1884.7368 - fn: 174.3684 - accuracy: 0.7836 - precision: 0.4495 - recall: 0.6846 - auc: 0.8295 - prc: 0.5753 - val_loss: 0.4764 - val_tp: 225.0000 - val_fp: 213.0000 - val_tn: 870.0000 - val_fn: 92.0000 - val_accuracy: 0.7821 - val_precision: 0.5137 - val_recall: 0.7098 - val_auc: 0.8433 - val_prc: 0.6811
Epoch 165/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5139 - tp: 404.5263 - fp: 474.1053 - tn: 1842.2105 - fn: 177.4035 - accuracy: 0.7751 - precision: 0.4576 - recall: 0.6915 - auc: 0.8274 - prc: 0.6055 - val_loss: 0.4773 - val_tp: 225.0000 - val_fp: 213.0000 - val_tn: 870.0000 - val_fn: 92.0000 - val_accuracy: 0.7821 - val_precision: 0.5137 - val_recall: 0.7098 - val_auc: 0.8440 - val_prc: 0.6811
Epoch 166/200
56/56 [==============================] - 0s 2ms/step - loss: 0.4826 - tp: 403.4912 - fp: 444.2456 - tn: 1888.1404 - fn: 162.3684 - accuracy: 0.7934 - precision: 0.4694 - recall: 0.7180 - auc: 0.8451 - prc: 0.6096 - val_loss: 0.4721 - val_tp: 225.0000 - val_fp: 204.0000 - val_tn: 879.0000 - val_fn: 92.0000 - val_accuracy: 0.7886 - val_precision: 0.5245 - val_recall: 0.7098 - val_auc: 0.8442 - val_prc: 0.6827
Epoch 167/200
56/56 [==============================] - 0s 2ms/step - loss: 0.4901 - tp: 406.7018 - fp: 456.0702 - tn: 1862.0526 - fn: 173.4211 - accuracy: 0.7857 - precision: 0.4707 - recall: 0.7130 - auc: 0.8408 - prc: 0.6223 - val_loss: 0.4765 - val_tp: 227.0000 - val_fp: 212.0000 - val_tn: 871.0000 - val_fn: 90.0000 - val_accuracy: 0.7843 - val_precision: 0.5171 - val_recall: 0.7161 - val_auc: 0.8442 - val_prc: 0.6823
Epoch 168/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5136 - tp: 360.8772 - fp: 463.5614 - tn: 1887.2456 - fn: 186.5614 - accuracy: 0.7755 - precision: 0.4326 - recall: 0.6510 - auc: 0.8096 - prc: 0.5594 - val_loss: 0.4765 - val_tp: 226.0000 - val_fp: 208.0000 - val_tn: 875.0000 - val_fn: 91.0000 - val_accuracy: 0.7864 - val_precision: 0.5207 - val_recall: 0.7129 - val_auc: 0.8441 - val_prc: 0.6817
Epoch 169/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5028 - tp: 401.0877 - fp: 473.9474 - tn: 1852.0877 - fn: 171.1228 - accuracy: 0.7747 - precision: 0.4510 - recall: 0.7035 - auc: 0.8316 - prc: 0.5989 - val_loss: 0.4788 - val_tp: 229.0000 - val_fp: 215.0000 - val_tn: 868.0000 - val_fn: 88.0000 - val_accuracy: 0.7836 - val_precision: 0.5158 - val_recall: 0.7224 - val_auc: 0.8441 - val_prc: 0.6818
Epoch 170/200
56/56 [==============================] - 0s 2ms/step - loss: 0.4972 - tp: 400.5614 - fp: 478.8947 - tn: 1843.1930 - fn: 175.5965 - accuracy: 0.7749 - precision: 0.4523 - recall: 0.6981 - auc: 0.8324 - prc: 0.6205 - val_loss: 0.4781 - val_tp: 228.0000 - val_fp: 214.0000 - val_tn: 869.0000 - val_fn: 89.0000 - val_accuracy: 0.7836 - val_precision: 0.5158 - val_recall: 0.7192 - val_auc: 0.8437 - val_prc: 0.6812
Epoch 171/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5201 - tp: 401.4737 - fp: 455.4912 - tn: 1862.1053 - fn: 179.1754 - accuracy: 0.7773 - precision: 0.4607 - recall: 0.6771 - auc: 0.8177 - prc: 0.5990 - val_loss: 0.4749 - val_tp: 227.0000 - val_fp: 208.0000 - val_tn: 875.0000 - val_fn: 90.0000 - val_accuracy: 0.7871 - val_precision: 0.5218 - val_recall: 0.7161 - val_auc: 0.8444 - val_prc: 0.6827
Epoch 172/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5228 - tp: 407.3158 - fp: 457.0702 - tn: 1856.7018 - fn: 177.1579 - accuracy: 0.7795 - precision: 0.4701 - recall: 0.7031 - auc: 0.8235 - prc: 0.6009 - val_loss: 0.4764 - val_tp: 225.0000 - val_fp: 206.0000 - val_tn: 877.0000 - val_fn: 92.0000 - val_accuracy: 0.7871 - val_precision: 0.5220 - val_recall: 0.7098 - val_auc: 0.8443 - val_prc: 0.6833
Epoch 173/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5029 - tp: 403.5614 - fp: 466.4211 - tn: 1849.7895 - fn: 178.4737 - accuracy: 0.7778 - precision: 0.4628 - recall: 0.6995 - auc: 0.8329 - prc: 0.6209 - val_loss: 0.4748 - val_tp: 224.0000 - val_fp: 206.0000 - val_tn: 877.0000 - val_fn: 93.0000 - val_accuracy: 0.7864 - val_precision: 0.5209 - val_recall: 0.7066 - val_auc: 0.8446 - val_prc: 0.6835
Epoch 174/200
56/56 [==============================] - 0s 2ms/step - loss: 0.4950 - tp: 413.2281 - fp: 448.0526 - tn: 1865.5789 - fn: 171.3860 - accuracy: 0.7889 - precision: 0.4860 - recall: 0.7138 - auc: 0.8406 - prc: 0.6514 - val_loss: 0.4732 - val_tp: 222.0000 - val_fp: 204.0000 - val_tn: 879.0000 - val_fn: 95.0000 - val_accuracy: 0.7864 - val_precision: 0.5211 - val_recall: 0.7003 - val_auc: 0.8450 - val_prc: 0.6839
Epoch 175/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5091 - tp: 389.0526 - fp: 465.1930 - tn: 1863.1754 - fn: 180.8246 - accuracy: 0.7767 - precision: 0.4529 - recall: 0.6721 - auc: 0.8257 - prc: 0.5841 - val_loss: 0.4725 - val_tp: 222.0000 - val_fp: 200.0000 - val_tn: 883.0000 - val_fn: 95.0000 - val_accuracy: 0.7893 - val_precision: 0.5261 - val_recall: 0.7003 - val_auc: 0.8446 - val_prc: 0.6826
Epoch 176/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5148 - tp: 403.0175 - fp: 454.5439 - tn: 1858.7895 - fn: 181.8947 - accuracy: 0.7818 - precision: 0.4799 - recall: 0.6960 - auc: 0.8317 - prc: 0.6114 - val_loss: 0.4746 - val_tp: 222.0000 - val_fp: 203.0000 - val_tn: 880.0000 - val_fn: 95.0000 - val_accuracy: 0.7871 - val_precision: 0.5224 - val_recall: 0.7003 - val_auc: 0.8452 - val_prc: 0.6839
Epoch 177/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5070 - tp: 395.7193 - fp: 453.5614 - tn: 1868.0877 - fn: 180.8772 - accuracy: 0.7815 - precision: 0.4720 - recall: 0.6903 - auc: 0.8312 - prc: 0.6223 - val_loss: 0.4717 - val_tp: 223.0000 - val_fp: 199.0000 - val_tn: 884.0000 - val_fn: 94.0000 - val_accuracy: 0.7907 - val_precision: 0.5284 - val_recall: 0.7035 - val_auc: 0.8449 - val_prc: 0.6834
Epoch 178/200
56/56 [==============================] - 0s 2ms/step - loss: 0.4954 - tp: 400.6842 - fp: 461.1228 - tn: 1873.3509 - fn: 163.0877 - accuracy: 0.7829 - precision: 0.4559 - recall: 0.7165 - auc: 0.8351 - prc: 0.5944 - val_loss: 0.4749 - val_tp: 224.0000 - val_fp: 206.0000 - val_tn: 877.0000 - val_fn: 93.0000 - val_accuracy: 0.7864 - val_precision: 0.5209 - val_recall: 0.7066 - val_auc: 0.8449 - val_prc: 0.6830
Epoch 179/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5123 - tp: 416.4561 - fp: 462.2982 - tn: 1841.5263 - fn: 177.9649 - accuracy: 0.7748 - precision: 0.4740 - recall: 0.7037 - auc: 0.8335 - prc: 0.6068 - val_loss: 0.4753 - val_tp: 223.0000 - val_fp: 205.0000 - val_tn: 878.0000 - val_fn: 94.0000 - val_accuracy: 0.7864 - val_precision: 0.5210 - val_recall: 0.7035 - val_auc: 0.8456 - val_prc: 0.6836
Epoch 180/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5019 - tp: 399.7193 - fp: 452.6842 - tn: 1875.5439 - fn: 170.2982 - accuracy: 0.7838 - precision: 0.4619 - recall: 0.6981 - auc: 0.8266 - prc: 0.5976 - val_loss: 0.4697 - val_tp: 220.0000 - val_fp: 196.0000 - val_tn: 887.0000 - val_fn: 97.0000 - val_accuracy: 0.7907 - val_precision: 0.5288 - val_recall: 0.6940 - val_auc: 0.8454 - val_prc: 0.6840
Epoch 181/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5057 - tp: 400.5088 - fp: 440.2632 - tn: 1877.6316 - fn: 179.8421 - accuracy: 0.7873 - precision: 0.4811 - recall: 0.6863 - auc: 0.8301 - prc: 0.6228 - val_loss: 0.4786 - val_tp: 229.0000 - val_fp: 215.0000 - val_tn: 868.0000 - val_fn: 88.0000 - val_accuracy: 0.7836 - val_precision: 0.5158 - val_recall: 0.7224 - val_auc: 0.8450 - val_prc: 0.6825
Epoch 182/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5061 - tp: 392.5965 - fp: 459.1754 - tn: 1866.5614 - fn: 179.9123 - accuracy: 0.7778 - precision: 0.4620 - recall: 0.6883 - auc: 0.8281 - prc: 0.6052 - val_loss: 0.4721 - val_tp: 224.0000 - val_fp: 205.0000 - val_tn: 878.0000 - val_fn: 93.0000 - val_accuracy: 0.7871 - val_precision: 0.5221 - val_recall: 0.7066 - val_auc: 0.8457 - val_prc: 0.6839
Epoch 183/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5143 - tp: 393.0877 - fp: 463.6140 - tn: 1871.9298 - fn: 169.6140 - accuracy: 0.7762 - precision: 0.4483 - recall: 0.6873 - auc: 0.8200 - prc: 0.5812 - val_loss: 0.4713 - val_tp: 222.0000 - val_fp: 201.0000 - val_tn: 882.0000 - val_fn: 95.0000 - val_accuracy: 0.7886 - val_precision: 0.5248 - val_recall: 0.7003 - val_auc: 0.8456 - val_prc: 0.6829
Epoch 184/200
56/56 [==============================] - 0s 2ms/step - loss: 0.4969 - tp: 410.8596 - fp: 455.3860 - tn: 1865.8947 - fn: 166.1053 - accuracy: 0.7905 - precision: 0.4884 - recall: 0.7146 - auc: 0.8387 - prc: 0.6214 - val_loss: 0.4706 - val_tp: 221.0000 - val_fp: 199.0000 - val_tn: 884.0000 - val_fn: 96.0000 - val_accuracy: 0.7893 - val_precision: 0.5262 - val_recall: 0.6972 - val_auc: 0.8458 - val_prc: 0.6836
Epoch 185/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5143 - tp: 393.9649 - fp: 444.3684 - tn: 1877.7895 - fn: 182.1228 - accuracy: 0.7830 - precision: 0.4638 - recall: 0.6714 - auc: 0.8240 - prc: 0.5676 - val_loss: 0.4669 - val_tp: 220.0000 - val_fp: 196.0000 - val_tn: 887.0000 - val_fn: 97.0000 - val_accuracy: 0.7907 - val_precision: 0.5288 - val_recall: 0.6940 - val_auc: 0.8455 - val_prc: 0.6833
Epoch 186/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5027 - tp: 397.3684 - fp: 436.0175 - tn: 1893.2982 - fn: 171.5614 - accuracy: 0.7871 - precision: 0.4662 - recall: 0.7001 - auc: 0.8303 - prc: 0.5978 - val_loss: 0.4751 - val_tp: 225.0000 - val_fp: 207.0000 - val_tn: 876.0000 - val_fn: 92.0000 - val_accuracy: 0.7864 - val_precision: 0.5208 - val_recall: 0.7098 - val_auc: 0.8443 - val_prc: 0.6814
Epoch 187/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5260 - tp: 401.2632 - fp: 482.5789 - tn: 1843.7193 - fn: 170.6842 - accuracy: 0.7724 - precision: 0.4496 - recall: 0.6986 - auc: 0.8206 - prc: 0.5922 - val_loss: 0.4760 - val_tp: 222.0000 - val_fp: 210.0000 - val_tn: 873.0000 - val_fn: 95.0000 - val_accuracy: 0.7821 - val_precision: 0.5139 - val_recall: 0.7003 - val_auc: 0.8439 - val_prc: 0.6810
Epoch 188/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5156 - tp: 404.3509 - fp: 457.6140 - tn: 1855.8246 - fn: 180.4561 - accuracy: 0.7794 - precision: 0.4721 - recall: 0.6924 - auc: 0.8264 - prc: 0.6012 - val_loss: 0.4746 - val_tp: 223.0000 - val_fp: 204.0000 - val_tn: 879.0000 - val_fn: 94.0000 - val_accuracy: 0.7871 - val_precision: 0.5222 - val_recall: 0.7035 - val_auc: 0.8440 - val_prc: 0.6812
Epoch 189/200
56/56 [==============================] - 0s 2ms/step - loss: 0.4936 - tp: 402.7544 - fp: 439.2456 - tn: 1893.0702 - fn: 163.1754 - accuracy: 0.7962 - precision: 0.4745 - recall: 0.7052 - auc: 0.8311 - prc: 0.6082 - val_loss: 0.4760 - val_tp: 223.0000 - val_fp: 205.0000 - val_tn: 878.0000 - val_fn: 94.0000 - val_accuracy: 0.7864 - val_precision: 0.5210 - val_recall: 0.7035 - val_auc: 0.8444 - val_prc: 0.6810
Epoch 190/200
56/56 [==============================] - 0s 2ms/step - loss: 0.4952 - tp: 397.3860 - fp: 451.4912 - tn: 1877.4386 - fn: 171.9298 - accuracy: 0.7882 - precision: 0.4736 - recall: 0.7095 - auc: 0.8391 - prc: 0.6171 - val_loss: 0.4720 - val_tp: 221.0000 - val_fp: 199.0000 - val_tn: 884.0000 - val_fn: 96.0000 - val_accuracy: 0.7893 - val_precision: 0.5262 - val_recall: 0.6972 - val_auc: 0.8455 - val_prc: 0.6830
Epoch 191/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5050 - tp: 391.4912 - fp: 453.7895 - tn: 1873.1228 - fn: 179.8421 - accuracy: 0.7826 - precision: 0.4600 - recall: 0.6874 - auc: 0.8277 - prc: 0.5924 - val_loss: 0.4786 - val_tp: 226.0000 - val_fp: 211.0000 - val_tn: 872.0000 - val_fn: 91.0000 - val_accuracy: 0.7843 - val_precision: 0.5172 - val_recall: 0.7129 - val_auc: 0.8449 - val_prc: 0.6820
Epoch 192/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5125 - tp: 405.4561 - fp: 448.0877 - tn: 1873.6491 - fn: 171.0526 - accuracy: 0.7873 - precision: 0.4798 - recall: 0.7108 - auc: 0.8277 - prc: 0.6068 - val_loss: 0.4758 - val_tp: 223.0000 - val_fp: 206.0000 - val_tn: 877.0000 - val_fn: 94.0000 - val_accuracy: 0.7857 - val_precision: 0.5198 - val_recall: 0.7035 - val_auc: 0.8458 - val_prc: 0.6834
Epoch 193/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5061 - tp: 402.3509 - fp: 487.0175 - tn: 1840.8070 - fn: 168.0702 - accuracy: 0.7741 - precision: 0.4531 - recall: 0.7045 - auc: 0.8262 - prc: 0.6057 - val_loss: 0.4710 - val_tp: 221.0000 - val_fp: 202.0000 - val_tn: 881.0000 - val_fn: 96.0000 - val_accuracy: 0.7871 - val_precision: 0.5225 - val_recall: 0.6972 - val_auc: 0.8454 - val_prc: 0.6836
Epoch 194/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5095 - tp: 379.2807 - fp: 447.4386 - tn: 1885.7719 - fn: 185.7544 - accuracy: 0.7815 - precision: 0.4511 - recall: 0.6690 - auc: 0.8218 - prc: 0.5659 - val_loss: 0.4744 - val_tp: 224.0000 - val_fp: 204.0000 - val_tn: 879.0000 - val_fn: 93.0000 - val_accuracy: 0.7879 - val_precision: 0.5234 - val_recall: 0.7066 - val_auc: 0.8454 - val_prc: 0.6836
Epoch 195/200
56/56 [==============================] - 0s 2ms/step - loss: 0.4952 - tp: 388.5439 - fp: 455.6491 - tn: 1878.0877 - fn: 175.9649 - accuracy: 0.7814 - precision: 0.4619 - recall: 0.6881 - auc: 0.8360 - prc: 0.6177 - val_loss: 0.4663 - val_tp: 218.0000 - val_fp: 192.0000 - val_tn: 891.0000 - val_fn: 99.0000 - val_accuracy: 0.7921 - val_precision: 0.5317 - val_recall: 0.6877 - val_auc: 0.8453 - val_prc: 0.6833
Epoch 196/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5098 - tp: 398.4737 - fp: 459.7368 - tn: 1863.4211 - fn: 176.6140 - accuracy: 0.7813 - precision: 0.4531 - recall: 0.6841 - auc: 0.8228 - prc: 0.5831 - val_loss: 0.4748 - val_tp: 222.0000 - val_fp: 206.0000 - val_tn: 877.0000 - val_fn: 95.0000 - val_accuracy: 0.7850 - val_precision: 0.5187 - val_recall: 0.7003 - val_auc: 0.8450 - val_prc: 0.6828
Epoch 197/200
56/56 [==============================] - 0s 2ms/step - loss: 0.4959 - tp: 386.5088 - fp: 445.6316 - tn: 1891.4561 - fn: 174.6491 - accuracy: 0.7869 - precision: 0.4681 - recall: 0.6896 - auc: 0.8361 - prc: 0.5958 - val_loss: 0.4716 - val_tp: 218.0000 - val_fp: 203.0000 - val_tn: 880.0000 - val_fn: 99.0000 - val_accuracy: 0.7843 - val_precision: 0.5178 - val_recall: 0.6877 - val_auc: 0.8448 - val_prc: 0.6821
Epoch 198/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5041 - tp: 398.7895 - fp: 468.5439 - tn: 1852.5439 - fn: 178.3684 - accuracy: 0.7751 - precision: 0.4608 - recall: 0.6937 - auc: 0.8297 - prc: 0.6086 - val_loss: 0.4701 - val_tp: 220.0000 - val_fp: 197.0000 - val_tn: 886.0000 - val_fn: 97.0000 - val_accuracy: 0.7900 - val_precision: 0.5276 - val_recall: 0.6940 - val_auc: 0.8447 - val_prc: 0.6816
Epoch 199/200
56/56 [==============================] - 0s 2ms/step - loss: 0.4981 - tp: 405.5263 - fp: 432.7895 - tn: 1887.2456 - fn: 172.6842 - accuracy: 0.7921 - precision: 0.4824 - recall: 0.7057 - auc: 0.8358 - prc: 0.6181 - val_loss: 0.4709 - val_tp: 219.0000 - val_fp: 197.0000 - val_tn: 886.0000 - val_fn: 98.0000 - val_accuracy: 0.7893 - val_precision: 0.5264 - val_recall: 0.6909 - val_auc: 0.8447 - val_prc: 0.6819
Epoch 200/200
56/56 [==============================] - 0s 2ms/step - loss: 0.5352 - tp: 386.9474 - fp: 439.9474 - tn: 1877.1579 - fn: 194.1930 - accuracy: 0.7755 - precision: 0.4584 - recall: 0.6500 - auc: 0.8079 - prc: 0.5764 - val_loss: 0.4735 - val_tp: 221.0000 - val_fp: 199.0000 - val_tn: 884.0000 - val_fn: 96.0000 - val_accuracy: 0.7893 - val_precision: 0.5262 - val_recall: 0.6972 - val_auc: 0.8444 - val_prc: 0.6814
CPU times: user 39.6 s, sys: 8.15 s, total: 47.8 s
Wall time: 24.4 s


model2.summary()

Model: "sequential_1"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense_2 (Dense)              (None, 16)                192       
_________________________________________________________________
dropout (Dropout)            (None, 16)                0         
_________________________________________________________________
dense_3 (Dense)              (None, 1)                 17        
=================================================================
Total params: 209
Trainable params: 209
Non-trainable params: 0
_________________________________________________________________


history_df = pd.DataFrame(history2.history)
history_df['epoch']=history2.epoch
display(history_df)
train_acc = history_df.loc[199,'accuracy']
train_recall = history_df.loc[199,'recall']
train_loss = history_df.loc[199,'loss']


results_df = results_df['model1']

results2=model2.evaluate(X_test, y_test.values)

temp_df = pd.DataFrame(results2, index=model2.metrics_names, columns=['model2'])

results_df = pd.merge(results_df, temp_df, left_index=True, right_index=True)

results_df

94/94 [==============================] - 1s 2ms/step - loss: 0.4727 - tp: 443.0000 - fp: 450.0000 - tn: 1939.0000 - fn: 168.0000 - accuracy: 0.7940 - precision: 0.4961 - recall: 0.7250 - auc: 0.8465 - prc: 0.6692


plt.figure(figsize=(10,10))
plot_metrics(history2)


y_predict = (model2.predict(X_test) > THRESHOLD).astype('int32')
make_confusion_matrix(model2,y_test, y_predict, cmap='coolwarm')


print(f'Model test loss is: {results_df.loc["loss","model2"]:0.4f}, train loss is {train_loss:0.4f}')
print(f'Model test accuracy is: {results_df.loc["accuracy","model2"]:0.4f}, train accuracy is {train_acc:0.4f}')
print(f'Model test recall is: {results_df.loc["recall","model2"]:0.4f}, train recall is {train_recall:0.4f}')

Model test loss is: 0.4727, train loss is 0.5131
Model test accuracy is: 0.7940, train accuracy is 0.7814
Model test recall is: 0.7250, train recall is 0.6826


%%time
model3 = make_model(dropout=True, learning_rate=0.001, activation='tanh')

history3 = model3.fit(X_train, y_train, epochs=EPOCHS+100, batch_size=BATCH_SIZE, use_multiprocessing=True, validation_split=0.2, class_weight=class_weight, verbose=0)

CPU times: user 34.8 s, sys: 6.49 s, total: 41.3 s
Wall time: 21.2 s


results_df = results_df.loc[:,['model1','model2']]

results3=model3.evaluate(X_test, y_test.values)

temp_df = pd.DataFrame(results3, index=model3.metrics_names, columns=['model2-tanh'])

results_df = pd.merge(results_df, temp_df, left_index=True, right_index=True)

results_df

94/94 [==============================] - 1s 1ms/step - loss: 0.4943 - tp: 434.0000 - fp: 528.0000 - tn: 1861.0000 - fn: 177.0000 - accuracy: 0.7650 - precision: 0.4511 - recall: 0.7103 - auc: 0.8221 - prc: 0.5886


print(f'Model test loss is: {results_df.loc["loss","model2-tanh"]:0.4f}')
print(f'Model test accuracy is: {results_df.loc["accuracy","model2-tanh"]:0.4f}')
print(f'Model test recall is: {results_df.loc["recall","model2-tanh"]:0.4f}')

Model test loss is: 0.4943
Model test accuracy is: 0.7650
Model test recall is: 0.7103


%%time
model4 = make_model2(dropout=True, learning_rate=0.002) 
# using output_bias formula per keras tutorial but scaling by factor of 10 so as to not overemphasize accuracy (helps improve recall)

history4 = model4.fit(X_train, y_train, epochs=EPOCHS+100, batch_size=2000, use_multiprocessing=True, validation_split=0.2, class_weight=class_weight, verbose=1)

Epoch 1/200
3/3 [==============================] - 3s 537ms/step - loss: 0.8606 - tp: 505.7500 - fp: 669.0000 - tn: 5174.5000 - fn: 950.7500 - accuracy: 0.7796 - precision: 0.4339 - recall: 0.3584 - auc: 0.6333 - prc: 0.3957 - val_loss: 0.5261 - val_tp: 0.0000e+00 - val_fp: 0.0000e+00 - val_tn: 1083.0000 - val_fn: 317.0000 - val_accuracy: 0.7736 - val_precision: 0.0000e+00 - val_recall: 0.0000e+00 - val_auc: 0.6186 - val_prc: 0.3233
Epoch 2/200
3/3 [==============================] - 0s 17ms/step - loss: 0.8203 - tp: 136.0000 - fp: 424.5000 - tn: 3023.0000 - fn: 716.5000 - accuracy: 0.7362 - precision: 0.2447 - recall: 0.1575 - auc: 0.5421 - prc: 0.2242 - val_loss: 0.5288 - val_tp: 1.0000 - val_fp: 3.0000 - val_tn: 1080.0000 - val_fn: 316.0000 - val_accuracy: 0.7721 - val_precision: 0.2500 - val_recall: 0.0032 - val_auc: 0.6513 - val_prc: 0.3498
Epoch 3/200
3/3 [==============================] - 0s 18ms/step - loss: 0.7821 - tp: 183.2500 - fp: 531.2500 - tn: 2916.7500 - fn: 668.7500 - accuracy: 0.7228 - precision: 0.2552 - recall: 0.2120 - auc: 0.5598 - prc: 0.2376 - val_loss: 0.5353 - val_tp: 10.0000 - val_fp: 10.0000 - val_tn: 1073.0000 - val_fn: 307.0000 - val_accuracy: 0.7736 - val_precision: 0.5000 - val_recall: 0.0315 - val_auc: 0.6734 - val_prc: 0.3677
Epoch 4/200
3/3 [==============================] - 0s 17ms/step - loss: 0.7816 - tp: 224.5000 - fp: 654.0000 - tn: 2793.2500 - fn: 628.2500 - accuracy: 0.7030 - precision: 0.2570 - recall: 0.2627 - auc: 0.5498 - prc: 0.2374 - val_loss: 0.5427 - val_tp: 25.0000 - val_fp: 29.0000 - val_tn: 1054.0000 - val_fn: 292.0000 - val_accuracy: 0.7707 - val_precision: 0.4630 - val_recall: 0.0789 - val_auc: 0.6929 - val_prc: 0.3816
Epoch 5/200
3/3 [==============================] - 0s 18ms/step - loss: 0.7672 - tp: 257.7500 - fp: 787.5000 - tn: 2668.2500 - fn: 586.5000 - accuracy: 0.6813 - precision: 0.2462 - recall: 0.3061 - auc: 0.5507 - prc: 0.2354 - val_loss: 0.5486 - val_tp: 44.0000 - val_fp: 55.0000 - val_tn: 1028.0000 - val_fn: 273.0000 - val_accuracy: 0.7657 - val_precision: 0.4444 - val_recall: 0.1388 - val_auc: 0.7094 - val_prc: 0.3914
Epoch 6/200
3/3 [==============================] - 0s 20ms/step - loss: 0.7653 - tp: 290.5000 - fp: 823.0000 - tn: 2620.7500 - fn: 565.7500 - accuracy: 0.6744 - precision: 0.2581 - recall: 0.3354 - auc: 0.5618 - prc: 0.2442 - val_loss: 0.5519 - val_tp: 71.0000 - val_fp: 73.0000 - val_tn: 1010.0000 - val_fn: 246.0000 - val_accuracy: 0.7721 - val_precision: 0.4931 - val_recall: 0.2240 - val_auc: 0.7217 - val_prc: 0.3990
Epoch 7/200
3/3 [==============================] - 0s 18ms/step - loss: 0.7444 - tp: 309.0000 - fp: 837.2500 - tn: 2615.0000 - fn: 538.7500 - accuracy: 0.6802 - precision: 0.2698 - recall: 0.3653 - auc: 0.5753 - prc: 0.2653 - val_loss: 0.5522 - val_tp: 87.0000 - val_fp: 87.0000 - val_tn: 996.0000 - val_fn: 230.0000 - val_accuracy: 0.7736 - val_precision: 0.5000 - val_recall: 0.2744 - val_auc: 0.7329 - val_prc: 0.4031
Epoch 8/200
3/3 [==============================] - 0s 17ms/step - loss: 0.7295 - tp: 309.2500 - fp: 868.0000 - tn: 2582.7500 - fn: 540.0000 - accuracy: 0.6733 - precision: 0.2621 - recall: 0.3625 - auc: 0.5876 - prc: 0.2782 - val_loss: 0.5502 - val_tp: 100.0000 - val_fp: 94.0000 - val_tn: 989.0000 - val_fn: 217.0000 - val_accuracy: 0.7779 - val_precision: 0.5155 - val_recall: 0.3155 - val_auc: 0.7408 - val_prc: 0.4075
Epoch 9/200
3/3 [==============================] - 0s 17ms/step - loss: 0.7064 - tp: 357.7500 - fp: 854.0000 - tn: 2603.5000 - fn: 484.7500 - accuracy: 0.6897 - precision: 0.2937 - recall: 0.4241 - auc: 0.6114 - prc: 0.2811 - val_loss: 0.5468 - val_tp: 103.0000 - val_fp: 101.0000 - val_tn: 982.0000 - val_fn: 214.0000 - val_accuracy: 0.7750 - val_precision: 0.5049 - val_recall: 0.3249 - val_auc: 0.7465 - val_prc: 0.4115
Epoch 10/200
3/3 [==============================] - 0s 18ms/step - loss: 0.7090 - tp: 346.2500 - fp: 807.7500 - tn: 2633.2500 - fn: 512.7500 - accuracy: 0.6917 - precision: 0.3014 - recall: 0.4040 - auc: 0.6234 - prc: 0.3082 - val_loss: 0.5436 - val_tp: 103.0000 - val_fp: 105.0000 - val_tn: 978.0000 - val_fn: 214.0000 - val_accuracy: 0.7721 - val_precision: 0.4952 - val_recall: 0.3249 - val_auc: 0.7505 - val_prc: 0.4133
Epoch 11/200
3/3 [==============================] - 0s 18ms/step - loss: 0.7058 - tp: 337.2500 - fp: 780.2500 - tn: 2666.7500 - fn: 515.7500 - accuracy: 0.6963 - precision: 0.2989 - recall: 0.3927 - auc: 0.6253 - prc: 0.2899 - val_loss: 0.5407 - val_tp: 107.0000 - val_fp: 108.0000 - val_tn: 975.0000 - val_fn: 210.0000 - val_accuracy: 0.7729 - val_precision: 0.4977 - val_recall: 0.3375 - val_auc: 0.7544 - val_prc: 0.4160
Epoch 12/200
3/3 [==============================] - 0s 19ms/step - loss: 0.6991 - tp: 342.0000 - fp: 794.2500 - tn: 2664.0000 - fn: 499.7500 - accuracy: 0.7008 - precision: 0.3009 - recall: 0.4087 - auc: 0.6179 - prc: 0.2994 - val_loss: 0.5373 - val_tp: 111.0000 - val_fp: 109.0000 - val_tn: 974.0000 - val_fn: 206.0000 - val_accuracy: 0.7750 - val_precision: 0.5045 - val_recall: 0.3502 - val_auc: 0.7557 - val_prc: 0.4169
Epoch 13/200
3/3 [==============================] - 0s 19ms/step - loss: 0.6807 - tp: 351.5000 - fp: 754.2500 - tn: 2702.0000 - fn: 492.2500 - accuracy: 0.7101 - precision: 0.3158 - recall: 0.4183 - auc: 0.6512 - prc: 0.3054 - val_loss: 0.5345 - val_tp: 113.0000 - val_fp: 111.0000 - val_tn: 972.0000 - val_fn: 204.0000 - val_accuracy: 0.7750 - val_precision: 0.5045 - val_recall: 0.3565 - val_auc: 0.7582 - val_prc: 0.4190
Epoch 14/200
3/3 [==============================] - 0s 19ms/step - loss: 0.7001 - tp: 341.7500 - fp: 726.5000 - tn: 2724.5000 - fn: 507.2500 - accuracy: 0.7129 - precision: 0.3189 - recall: 0.4022 - auc: 0.6252 - prc: 0.3007 - val_loss: 0.5325 - val_tp: 120.0000 - val_fp: 113.0000 - val_tn: 970.0000 - val_fn: 197.0000 - val_accuracy: 0.7786 - val_precision: 0.5150 - val_recall: 0.3785 - val_auc: 0.7602 - val_prc: 0.4208
Epoch 15/200
3/3 [==============================] - 0s 17ms/step - loss: 0.6790 - tp: 359.2500 - fp: 726.2500 - tn: 2728.5000 - fn: 486.0000 - accuracy: 0.7172 - precision: 0.3279 - recall: 0.4258 - auc: 0.6537 - prc: 0.3237 - val_loss: 0.5311 - val_tp: 124.0000 - val_fp: 117.0000 - val_tn: 966.0000 - val_fn: 193.0000 - val_accuracy: 0.7786 - val_precision: 0.5145 - val_recall: 0.3912 - val_auc: 0.7611 - val_prc: 0.4216
Epoch 16/200
3/3 [==============================] - 0s 17ms/step - loss: 0.6877 - tp: 352.2500 - fp: 671.2500 - tn: 2776.7500 - fn: 499.7500 - accuracy: 0.7281 - precision: 0.3449 - recall: 0.4126 - auc: 0.6447 - prc: 0.3315 - val_loss: 0.5306 - val_tp: 125.0000 - val_fp: 122.0000 - val_tn: 961.0000 - val_fn: 192.0000 - val_accuracy: 0.7757 - val_precision: 0.5061 - val_recall: 0.3943 - val_auc: 0.7623 - val_prc: 0.4235
Epoch 17/200
3/3 [==============================] - 0s 18ms/step - loss: 0.6717 - tp: 356.7500 - fp: 658.5000 - tn: 2791.2500 - fn: 493.5000 - accuracy: 0.7310 - precision: 0.3482 - recall: 0.4172 - auc: 0.6638 - prc: 0.3424 - val_loss: 0.5308 - val_tp: 127.0000 - val_fp: 128.0000 - val_tn: 955.0000 - val_fn: 190.0000 - val_accuracy: 0.7729 - val_precision: 0.4980 - val_recall: 0.4006 - val_auc: 0.7636 - val_prc: 0.4250
Epoch 18/200
3/3 [==============================] - 0s 18ms/step - loss: 0.6806 - tp: 348.5000 - fp: 691.0000 - tn: 2761.2500 - fn: 499.2500 - accuracy: 0.7244 - precision: 0.3350 - recall: 0.4106 - auc: 0.6513 - prc: 0.3265 - val_loss: 0.5318 - val_tp: 131.0000 - val_fp: 137.0000 - val_tn: 946.0000 - val_fn: 186.0000 - val_accuracy: 0.7693 - val_precision: 0.4888 - val_recall: 0.4132 - val_auc: 0.7645 - val_prc: 0.4266
Epoch 19/200
3/3 [==============================] - 0s 19ms/step - loss: 0.6724 - tp: 370.5000 - fp: 680.7500 - tn: 2774.5000 - fn: 474.2500 - accuracy: 0.7301 - precision: 0.3475 - recall: 0.4366 - auc: 0.6635 - prc: 0.3248 - val_loss: 0.5326 - val_tp: 132.0000 - val_fp: 140.0000 - val_tn: 943.0000 - val_fn: 185.0000 - val_accuracy: 0.7679 - val_precision: 0.4853 - val_recall: 0.4164 - val_auc: 0.7657 - val_prc: 0.4279
Epoch 20/200
3/3 [==============================] - 0s 19ms/step - loss: 0.6567 - tp: 380.7500 - fp: 646.0000 - tn: 2803.0000 - fn: 470.2500 - accuracy: 0.7412 - precision: 0.3721 - recall: 0.4467 - auc: 0.6830 - prc: 0.3558 - val_loss: 0.5335 - val_tp: 137.0000 - val_fp: 147.0000 - val_tn: 936.0000 - val_fn: 180.0000 - val_accuracy: 0.7664 - val_precision: 0.4824 - val_recall: 0.4322 - val_auc: 0.7664 - val_prc: 0.4297
Epoch 21/200
3/3 [==============================] - 0s 17ms/step - loss: 0.6493 - tp: 396.2500 - fp: 658.7500 - tn: 2793.7500 - fn: 451.2500 - accuracy: 0.7421 - precision: 0.3742 - recall: 0.4703 - auc: 0.6931 - prc: 0.3549 - val_loss: 0.5348 - val_tp: 139.0000 - val_fp: 152.0000 - val_tn: 931.0000 - val_fn: 178.0000 - val_accuracy: 0.7643 - val_precision: 0.4777 - val_recall: 0.4385 - val_auc: 0.7674 - val_prc: 0.4313
Epoch 22/200
3/3 [==============================] - 0s 18ms/step - loss: 0.6834 - tp: 371.5000 - fp: 695.0000 - tn: 2750.2500 - fn: 483.2500 - accuracy: 0.7256 - precision: 0.3478 - recall: 0.4329 - auc: 0.6629 - prc: 0.3259 - val_loss: 0.5359 - val_tp: 144.0000 - val_fp: 155.0000 - val_tn: 928.0000 - val_fn: 173.0000 - val_accuracy: 0.7657 - val_precision: 0.4816 - val_recall: 0.4543 - val_auc: 0.7679 - val_prc: 0.4327
Epoch 23/200
3/3 [==============================] - 0s 16ms/step - loss: 0.6564 - tp: 390.5000 - fp: 692.7500 - tn: 2756.7500 - fn: 460.0000 - accuracy: 0.7304 - precision: 0.3560 - recall: 0.4563 - auc: 0.6861 - prc: 0.3551 - val_loss: 0.5355 - val_tp: 145.0000 - val_fp: 157.0000 - val_tn: 926.0000 - val_fn: 172.0000 - val_accuracy: 0.7650 - val_precision: 0.4801 - val_recall: 0.4574 - val_auc: 0.7689 - val_prc: 0.4345
Epoch 24/200
3/3 [==============================] - 0s 18ms/step - loss: 0.6708 - tp: 387.7500 - fp: 712.5000 - tn: 2729.7500 - fn: 470.0000 - accuracy: 0.7247 - precision: 0.3520 - recall: 0.4493 - auc: 0.6764 - prc: 0.3571 - val_loss: 0.5340 - val_tp: 144.0000 - val_fp: 157.0000 - val_tn: 926.0000 - val_fn: 173.0000 - val_accuracy: 0.7643 - val_precision: 0.4784 - val_recall: 0.4543 - val_auc: 0.7701 - val_prc: 0.4369
Epoch 25/200
3/3 [==============================] - 0s 19ms/step - loss: 0.6690 - tp: 388.0000 - fp: 692.2500 - tn: 2748.7500 - fn: 471.0000 - accuracy: 0.7276 - precision: 0.3592 - recall: 0.4501 - auc: 0.6835 - prc: 0.3544 - val_loss: 0.5318 - val_tp: 145.0000 - val_fp: 156.0000 - val_tn: 927.0000 - val_fn: 172.0000 - val_accuracy: 0.7657 - val_precision: 0.4817 - val_recall: 0.4574 - val_auc: 0.7706 - val_prc: 0.4384
Epoch 26/200
3/3 [==============================] - 0s 18ms/step - loss: 0.6488 - tp: 384.5000 - fp: 649.0000 - tn: 2812.2500 - fn: 454.2500 - accuracy: 0.7414 - precision: 0.3663 - recall: 0.4547 - auc: 0.6901 - prc: 0.3516 - val_loss: 0.5307 - val_tp: 146.0000 - val_fp: 155.0000 - val_tn: 928.0000 - val_fn: 171.0000 - val_accuracy: 0.7671 - val_precision: 0.4850 - val_recall: 0.4606 - val_auc: 0.7712 - val_prc: 0.4400
Epoch 27/200
3/3 [==============================] - 0s 16ms/step - loss: 0.6473 - tp: 399.5000 - fp: 685.7500 - tn: 2764.7500 - fn: 450.0000 - accuracy: 0.7339 - precision: 0.3652 - recall: 0.4700 - auc: 0.6997 - prc: 0.3704 - val_loss: 0.5306 - val_tp: 149.0000 - val_fp: 157.0000 - val_tn: 926.0000 - val_fn: 168.0000 - val_accuracy: 0.7679 - val_precision: 0.4869 - val_recall: 0.4700 - val_auc: 0.7718 - val_prc: 0.4421
Epoch 28/200
3/3 [==============================] - 0s 19ms/step - loss: 0.6465 - tp: 412.2500 - fp: 654.0000 - tn: 2786.7500 - fn: 447.0000 - accuracy: 0.7445 - precision: 0.3903 - recall: 0.4812 - auc: 0.7024 - prc: 0.3934 - val_loss: 0.5304 - val_tp: 149.0000 - val_fp: 156.0000 - val_tn: 927.0000 - val_fn: 168.0000 - val_accuracy: 0.7686 - val_precision: 0.4885 - val_recall: 0.4700 - val_auc: 0.7727 - val_prc: 0.4438
Epoch 29/200
3/3 [==============================] - 0s 17ms/step - loss: 0.6495 - tp: 398.5000 - fp: 634.0000 - tn: 2808.2500 - fn: 459.2500 - accuracy: 0.7444 - precision: 0.3850 - recall: 0.4611 - auc: 0.7021 - prc: 0.3813 - val_loss: 0.5299 - val_tp: 150.0000 - val_fp: 157.0000 - val_tn: 926.0000 - val_fn: 167.0000 - val_accuracy: 0.7686 - val_precision: 0.4886 - val_recall: 0.4732 - val_auc: 0.7735 - val_prc: 0.4460
Epoch 30/200
3/3 [==============================] - 0s 16ms/step - loss: 0.6483 - tp: 400.5000 - fp: 670.2500 - tn: 2776.7500 - fn: 452.5000 - accuracy: 0.7397 - precision: 0.3757 - recall: 0.4711 - auc: 0.7014 - prc: 0.3677 - val_loss: 0.5295 - val_tp: 151.0000 - val_fp: 160.0000 - val_tn: 923.0000 - val_fn: 166.0000 - val_accuracy: 0.7671 - val_precision: 0.4855 - val_recall: 0.4763 - val_auc: 0.7740 - val_prc: 0.4482
Epoch 31/200
3/3 [==============================] - 0s 18ms/step - loss: 0.6427 - tp: 386.0000 - fp: 640.0000 - tn: 2813.2500 - fn: 460.7500 - accuracy: 0.7453 - precision: 0.3774 - recall: 0.4568 - auc: 0.6985 - prc: 0.3764 - val_loss: 0.5290 - val_tp: 156.0000 - val_fp: 163.0000 - val_tn: 920.0000 - val_fn: 161.0000 - val_accuracy: 0.7686 - val_precision: 0.4890 - val_recall: 0.4921 - val_auc: 0.7743 - val_prc: 0.4502
Epoch 32/200
3/3 [==============================] - 0s 18ms/step - loss: 0.6401 - tp: 419.5000 - fp: 660.2500 - tn: 2787.0000 - fn: 433.2500 - accuracy: 0.7454 - precision: 0.3877 - recall: 0.4919 - auc: 0.7093 - prc: 0.3825 - val_loss: 0.5285 - val_tp: 156.0000 - val_fp: 164.0000 - val_tn: 919.0000 - val_fn: 161.0000 - val_accuracy: 0.7679 - val_precision: 0.4875 - val_recall: 0.4921 - val_auc: 0.7749 - val_prc: 0.4522
Epoch 33/200
3/3 [==============================] - 0s 19ms/step - loss: 0.6420 - tp: 398.7500 - fp: 656.5000 - tn: 2788.0000 - fn: 456.7500 - accuracy: 0.7398 - precision: 0.3772 - recall: 0.4659 - auc: 0.7155 - prc: 0.3785 - val_loss: 0.5285 - val_tp: 156.0000 - val_fp: 165.0000 - val_tn: 918.0000 - val_fn: 161.0000 - val_accuracy: 0.7671 - val_precision: 0.4860 - val_recall: 0.4921 - val_auc: 0.7757 - val_prc: 0.4539
Epoch 34/200
3/3 [==============================] - 0s 17ms/step - loss: 0.6341 - tp: 399.7500 - fp: 657.7500 - tn: 2788.7500 - fn: 453.7500 - accuracy: 0.7413 - precision: 0.3790 - recall: 0.4702 - auc: 0.7152 - prc: 0.4016 - val_loss: 0.5285 - val_tp: 158.0000 - val_fp: 166.0000 - val_tn: 917.0000 - val_fn: 159.0000 - val_accuracy: 0.7679 - val_precision: 0.4877 - val_recall: 0.4984 - val_auc: 0.7763 - val_prc: 0.4555
Epoch 35/200
3/3 [==============================] - 0s 17ms/step - loss: 0.6418 - tp: 395.7500 - fp: 658.0000 - tn: 2799.2500 - fn: 447.0000 - accuracy: 0.7425 - precision: 0.3734 - recall: 0.4677 - auc: 0.7055 - prc: 0.3749 - val_loss: 0.5277 - val_tp: 158.0000 - val_fp: 164.0000 - val_tn: 919.0000 - val_fn: 159.0000 - val_accuracy: 0.7693 - val_precision: 0.4907 - val_recall: 0.4984 - val_auc: 0.7772 - val_prc: 0.4577
Epoch 36/200
3/3 [==============================] - 0s 18ms/step - loss: 0.6345 - tp: 412.0000 - fp: 623.5000 - tn: 2818.5000 - fn: 446.0000 - accuracy: 0.7524 - precision: 0.4004 - recall: 0.4768 - auc: 0.7173 - prc: 0.4004 - val_loss: 0.5275 - val_tp: 159.0000 - val_fp: 164.0000 - val_tn: 919.0000 - val_fn: 158.0000 - val_accuracy: 0.7700 - val_precision: 0.4923 - val_recall: 0.5016 - val_auc: 0.7777 - val_prc: 0.4591
Epoch 37/200
3/3 [==============================] - 0s 17ms/step - loss: 0.6320 - tp: 399.5000 - fp: 610.2500 - tn: 2842.2500 - fn: 448.0000 - accuracy: 0.7534 - precision: 0.3938 - recall: 0.4709 - auc: 0.7181 - prc: 0.3880 - val_loss: 0.5265 - val_tp: 159.0000 - val_fp: 164.0000 - val_tn: 919.0000 - val_fn: 158.0000 - val_accuracy: 0.7700 - val_precision: 0.4923 - val_recall: 0.5016 - val_auc: 0.7786 - val_prc: 0.4627
Epoch 38/200
3/3 [==============================] - 0s 18ms/step - loss: 0.6269 - tp: 421.5000 - fp: 622.2500 - tn: 2827.5000 - fn: 428.7500 - accuracy: 0.7554 - precision: 0.4026 - recall: 0.4931 - auc: 0.7218 - prc: 0.4018 - val_loss: 0.5268 - val_tp: 160.0000 - val_fp: 168.0000 - val_tn: 915.0000 - val_fn: 157.0000 - val_accuracy: 0.7679 - val_precision: 0.4878 - val_recall: 0.5047 - val_auc: 0.7794 - val_prc: 0.4638
Epoch 39/200
3/3 [==============================] - 0s 17ms/step - loss: 0.6390 - tp: 404.0000 - fp: 652.0000 - tn: 2796.7500 - fn: 447.2500 - accuracy: 0.7443 - precision: 0.3817 - recall: 0.4736 - auc: 0.7193 - prc: 0.3748 - val_loss: 0.5270 - val_tp: 162.0000 - val_fp: 169.0000 - val_tn: 914.0000 - val_fn: 155.0000 - val_accuracy: 0.7686 - val_precision: 0.4894 - val_recall: 0.5110 - val_auc: 0.7805 - val_prc: 0.4660
Epoch 40/200
3/3 [==============================] - 0s 18ms/step - loss: 0.6374 - tp: 408.0000 - fp: 652.2500 - tn: 2788.7500 - fn: 451.0000 - accuracy: 0.7420 - precision: 0.3859 - recall: 0.4749 - auc: 0.7189 - prc: 0.3964 - val_loss: 0.5274 - val_tp: 164.0000 - val_fp: 169.0000 - val_tn: 914.0000 - val_fn: 153.0000 - val_accuracy: 0.7700 - val_precision: 0.4925 - val_recall: 0.5174 - val_auc: 0.7811 - val_prc: 0.4690
Epoch 41/200
3/3 [==============================] - 0s 17ms/step - loss: 0.6372 - tp: 414.0000 - fp: 664.0000 - tn: 2783.2500 - fn: 438.7500 - accuracy: 0.7442 - precision: 0.3857 - recall: 0.4879 - auc: 0.7089 - prc: 0.3916 - val_loss: 0.5270 - val_tp: 166.0000 - val_fp: 168.0000 - val_tn: 915.0000 - val_fn: 151.0000 - val_accuracy: 0.7721 - val_precision: 0.4970 - val_recall: 0.5237 - val_auc: 0.7816 - val_prc: 0.4730
Epoch 42/200
3/3 [==============================] - 0s 18ms/step - loss: 0.6073 - tp: 434.0000 - fp: 644.2500 - tn: 2809.0000 - fn: 412.7500 - accuracy: 0.7544 - precision: 0.4021 - recall: 0.5161 - auc: 0.7372 - prc: 0.4277 - val_loss: 0.5264 - val_tp: 167.0000 - val_fp: 169.0000 - val_tn: 914.0000 - val_fn: 150.0000 - val_accuracy: 0.7721 - val_precision: 0.4970 - val_recall: 0.5268 - val_auc: 0.7820 - val_prc: 0.4741
Epoch 43/200
3/3 [==============================] - 0s 17ms/step - loss: 0.6153 - tp: 434.0000 - fp: 594.5000 - tn: 2848.5000 - fn: 423.0000 - accuracy: 0.7652 - precision: 0.4273 - recall: 0.5093 - auc: 0.7413 - prc: 0.4194 - val_loss: 0.5268 - val_tp: 168.0000 - val_fp: 171.0000 - val_tn: 912.0000 - val_fn: 149.0000 - val_accuracy: 0.7714 - val_precision: 0.4956 - val_recall: 0.5300 - val_auc: 0.7827 - val_prc: 0.4770
Epoch 44/200
3/3 [==============================] - 0s 17ms/step - loss: 0.6220 - tp: 427.7500 - fp: 640.5000 - tn: 2810.2500 - fn: 421.5000 - accuracy: 0.7538 - precision: 0.4015 - recall: 0.5045 - auc: 0.7330 - prc: 0.4048 - val_loss: 0.5265 - val_tp: 169.0000 - val_fp: 175.0000 - val_tn: 908.0000 - val_fn: 148.0000 - val_accuracy: 0.7693 - val_precision: 0.4913 - val_recall: 0.5331 - val_auc: 0.7836 - val_prc: 0.4791
Epoch 45/200
3/3 [==============================] - 0s 19ms/step - loss: 0.6198 - tp: 432.2500 - fp: 635.2500 - tn: 2811.7500 - fn: 420.7500 - accuracy: 0.7544 - precision: 0.4050 - recall: 0.5061 - auc: 0.7333 - prc: 0.4123 - val_loss: 0.5272 - val_tp: 172.0000 - val_fp: 176.0000 - val_tn: 907.0000 - val_fn: 145.0000 - val_accuracy: 0.7707 - val_precision: 0.4943 - val_recall: 0.5426 - val_auc: 0.7844 - val_prc: 0.4809
Epoch 46/200
3/3 [==============================] - 0s 20ms/step - loss: 0.6170 - tp: 453.0000 - fp: 655.2500 - tn: 2789.7500 - fn: 402.0000 - accuracy: 0.7543 - precision: 0.4098 - recall: 0.5315 - auc: 0.7339 - prc: 0.4230 - val_loss: 0.5264 - val_tp: 174.0000 - val_fp: 177.0000 - val_tn: 906.0000 - val_fn: 143.0000 - val_accuracy: 0.7714 - val_precision: 0.4957 - val_recall: 0.5489 - val_auc: 0.7853 - val_prc: 0.4840
Epoch 47/200
3/3 [==============================] - 0s 19ms/step - loss: 0.6237 - tp: 435.5000 - fp: 648.0000 - tn: 2798.7500 - fn: 417.7500 - accuracy: 0.7519 - precision: 0.4017 - recall: 0.5108 - auc: 0.7270 - prc: 0.4179 - val_loss: 0.5242 - val_tp: 173.0000 - val_fp: 173.0000 - val_tn: 910.0000 - val_fn: 144.0000 - val_accuracy: 0.7736 - val_precision: 0.5000 - val_recall: 0.5457 - val_auc: 0.7862 - val_prc: 0.4864
Epoch 48/200
3/3 [==============================] - 0s 17ms/step - loss: 0.6077 - tp: 441.5000 - fp: 639.2500 - tn: 2808.0000 - fn: 411.2500 - accuracy: 0.7569 - precision: 0.4106 - recall: 0.5166 - auc: 0.7449 - prc: 0.4353 - val_loss: 0.5219 - val_tp: 173.0000 - val_fp: 172.0000 - val_tn: 911.0000 - val_fn: 144.0000 - val_accuracy: 0.7743 - val_precision: 0.5014 - val_recall: 0.5457 - val_auc: 0.7870 - val_prc: 0.4878
Epoch 49/200
3/3 [==============================] - 0s 19ms/step - loss: 0.6078 - tp: 464.2500 - fp: 643.2500 - tn: 2797.0000 - fn: 395.5000 - accuracy: 0.7586 - precision: 0.4220 - recall: 0.5424 - auc: 0.7504 - prc: 0.4258 - val_loss: 0.5210 - val_tp: 175.0000 - val_fp: 170.0000 - val_tn: 913.0000 - val_fn: 142.0000 - val_accuracy: 0.7771 - val_precision: 0.5072 - val_recall: 0.5521 - val_auc: 0.7880 - val_prc: 0.4921
Epoch 50/200
3/3 [==============================] - 0s 16ms/step - loss: 0.6166 - tp: 431.0000 - fp: 629.5000 - tn: 2814.2500 - fn: 425.2500 - accuracy: 0.7540 - precision: 0.4065 - recall: 0.5017 - auc: 0.7374 - prc: 0.4290 - val_loss: 0.5196 - val_tp: 175.0000 - val_fp: 170.0000 - val_tn: 913.0000 - val_fn: 142.0000 - val_accuracy: 0.7771 - val_precision: 0.5072 - val_recall: 0.5521 - val_auc: 0.7890 - val_prc: 0.4944
Epoch 51/200
3/3 [==============================] - 0s 20ms/step - loss: 0.6056 - tp: 449.5000 - fp: 594.0000 - tn: 2859.0000 - fn: 397.5000 - accuracy: 0.7711 - precision: 0.4316 - recall: 0.5325 - auc: 0.7445 - prc: 0.4187 - val_loss: 0.5176 - val_tp: 175.0000 - val_fp: 165.0000 - val_tn: 918.0000 - val_fn: 142.0000 - val_accuracy: 0.7807 - val_precision: 0.5147 - val_recall: 0.5521 - val_auc: 0.7900 - val_prc: 0.4969
Epoch 52/200
3/3 [==============================] - 0s 19ms/step - loss: 0.6124 - tp: 434.0000 - fp: 630.0000 - tn: 2814.7500 - fn: 421.2500 - accuracy: 0.7533 - precision: 0.4050 - recall: 0.5054 - auc: 0.7449 - prc: 0.4197 - val_loss: 0.5165 - val_tp: 175.0000 - val_fp: 166.0000 - val_tn: 917.0000 - val_fn: 142.0000 - val_accuracy: 0.7800 - val_precision: 0.5132 - val_recall: 0.5521 - val_auc: 0.7913 - val_prc: 0.5002
Epoch 53/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5930 - tp: 443.7500 - fp: 618.2500 - tn: 2845.7500 - fn: 392.2500 - accuracy: 0.7645 - precision: 0.4107 - recall: 0.5281 - auc: 0.7507 - prc: 0.4290 - val_loss: 0.5160 - val_tp: 177.0000 - val_fp: 166.0000 - val_tn: 917.0000 - val_fn: 140.0000 - val_accuracy: 0.7814 - val_precision: 0.5160 - val_recall: 0.5584 - val_auc: 0.7921 - val_prc: 0.5025
Epoch 54/200
3/3 [==============================] - 0s 17ms/step - loss: 0.6139 - tp: 407.7500 - fp: 636.2500 - tn: 2819.5000 - fn: 436.5000 - accuracy: 0.7502 - precision: 0.3881 - recall: 0.4820 - auc: 0.7356 - prc: 0.4065 - val_loss: 0.5167 - val_tp: 177.0000 - val_fp: 171.0000 - val_tn: 912.0000 - val_fn: 140.0000 - val_accuracy: 0.7779 - val_precision: 0.5086 - val_recall: 0.5584 - val_auc: 0.7925 - val_prc: 0.5043
Epoch 55/200
3/3 [==============================] - 0s 19ms/step - loss: 0.6048 - tp: 423.2500 - fp: 624.2500 - tn: 2830.5000 - fn: 422.0000 - accuracy: 0.7577 - precision: 0.4047 - recall: 0.5038 - auc: 0.7434 - prc: 0.4338 - val_loss: 0.5172 - val_tp: 179.0000 - val_fp: 172.0000 - val_tn: 911.0000 - val_fn: 138.0000 - val_accuracy: 0.7786 - val_precision: 0.5100 - val_recall: 0.5647 - val_auc: 0.7936 - val_prc: 0.5078
Epoch 56/200
3/3 [==============================] - 0s 22ms/step - loss: 0.6076 - tp: 443.2500 - fp: 607.7500 - tn: 2831.2500 - fn: 417.7500 - accuracy: 0.7621 - precision: 0.4263 - recall: 0.5148 - auc: 0.7470 - prc: 0.4529 - val_loss: 0.5183 - val_tp: 180.0000 - val_fp: 179.0000 - val_tn: 904.0000 - val_fn: 137.0000 - val_accuracy: 0.7743 - val_precision: 0.5014 - val_recall: 0.5678 - val_auc: 0.7947 - val_prc: 0.5093
Epoch 57/200
3/3 [==============================] - 0s 22ms/step - loss: 0.5996 - tp: 454.0000 - fp: 605.2500 - tn: 2843.5000 - fn: 397.2500 - accuracy: 0.7664 - precision: 0.4277 - recall: 0.5286 - auc: 0.7536 - prc: 0.4406 - val_loss: 0.5192 - val_tp: 180.0000 - val_fp: 180.0000 - val_tn: 903.0000 - val_fn: 137.0000 - val_accuracy: 0.7736 - val_precision: 0.5000 - val_recall: 0.5678 - val_auc: 0.7953 - val_prc: 0.5116
Epoch 58/200
3/3 [==============================] - 0s 22ms/step - loss: 0.6127 - tp: 433.0000 - fp: 655.2500 - tn: 2800.5000 - fn: 411.2500 - accuracy: 0.7517 - precision: 0.3948 - recall: 0.5136 - auc: 0.7328 - prc: 0.4180 - val_loss: 0.5186 - val_tp: 180.0000 - val_fp: 183.0000 - val_tn: 900.0000 - val_fn: 137.0000 - val_accuracy: 0.7714 - val_precision: 0.4959 - val_recall: 0.5678 - val_auc: 0.7959 - val_prc: 0.5145
Epoch 59/200
3/3 [==============================] - 0s 18ms/step - loss: 0.6147 - tp: 438.0000 - fp: 628.2500 - tn: 2822.5000 - fn: 411.2500 - accuracy: 0.7579 - precision: 0.4097 - recall: 0.5155 - auc: 0.7401 - prc: 0.4076 - val_loss: 0.5170 - val_tp: 179.0000 - val_fp: 181.0000 - val_tn: 902.0000 - val_fn: 138.0000 - val_accuracy: 0.7721 - val_precision: 0.4972 - val_recall: 0.5647 - val_auc: 0.7971 - val_prc: 0.5170
Epoch 60/200
3/3 [==============================] - 0s 19ms/step - loss: 0.6041 - tp: 459.2500 - fp: 606.0000 - tn: 2835.2500 - fn: 399.5000 - accuracy: 0.7656 - precision: 0.4317 - recall: 0.5337 - auc: 0.7508 - prc: 0.4438 - val_loss: 0.5160 - val_tp: 180.0000 - val_fp: 181.0000 - val_tn: 902.0000 - val_fn: 137.0000 - val_accuracy: 0.7729 - val_precision: 0.4986 - val_recall: 0.5678 - val_auc: 0.7981 - val_prc: 0.5194
Epoch 61/200
3/3 [==============================] - 0s 19ms/step - loss: 0.6095 - tp: 448.7500 - fp: 618.7500 - tn: 2823.2500 - fn: 409.2500 - accuracy: 0.7610 - precision: 0.4217 - recall: 0.5224 - auc: 0.7424 - prc: 0.4442 - val_loss: 0.5139 - val_tp: 179.0000 - val_fp: 178.0000 - val_tn: 905.0000 - val_fn: 138.0000 - val_accuracy: 0.7743 - val_precision: 0.5014 - val_recall: 0.5647 - val_auc: 0.7987 - val_prc: 0.5221
Epoch 62/200
3/3 [==============================] - 0s 20ms/step - loss: 0.6051 - tp: 423.5000 - fp: 636.7500 - tn: 2814.2500 - fn: 425.5000 - accuracy: 0.7530 - precision: 0.3989 - recall: 0.4980 - auc: 0.7506 - prc: 0.4286 - val_loss: 0.5118 - val_tp: 178.0000 - val_fp: 175.0000 - val_tn: 908.0000 - val_fn: 139.0000 - val_accuracy: 0.7757 - val_precision: 0.5042 - val_recall: 0.5615 - val_auc: 0.7995 - val_prc: 0.5244
Epoch 63/200
3/3 [==============================] - 0s 20ms/step - loss: 0.6039 - tp: 454.2500 - fp: 604.5000 - tn: 2844.7500 - fn: 396.5000 - accuracy: 0.7674 - precision: 0.4280 - recall: 0.5348 - auc: 0.7506 - prc: 0.4260 - val_loss: 0.5103 - val_tp: 179.0000 - val_fp: 175.0000 - val_tn: 908.0000 - val_fn: 138.0000 - val_accuracy: 0.7764 - val_precision: 0.5056 - val_recall: 0.5647 - val_auc: 0.8006 - val_prc: 0.5270
Epoch 64/200
3/3 [==============================] - 0s 20ms/step - loss: 0.6022 - tp: 421.7500 - fp: 581.7500 - tn: 2870.5000 - fn: 426.0000 - accuracy: 0.7654 - precision: 0.4185 - recall: 0.4942 - auc: 0.7541 - prc: 0.4305 - val_loss: 0.5098 - val_tp: 181.0000 - val_fp: 176.0000 - val_tn: 907.0000 - val_fn: 136.0000 - val_accuracy: 0.7771 - val_precision: 0.5070 - val_recall: 0.5710 - val_auc: 0.8011 - val_prc: 0.5290
Epoch 65/200
3/3 [==============================] - 0s 19ms/step - loss: 0.6029 - tp: 446.2500 - fp: 625.7500 - tn: 2824.5000 - fn: 403.5000 - accuracy: 0.7596 - precision: 0.4145 - recall: 0.5243 - auc: 0.7525 - prc: 0.4258 - val_loss: 0.5098 - val_tp: 182.0000 - val_fp: 178.0000 - val_tn: 905.0000 - val_fn: 135.0000 - val_accuracy: 0.7764 - val_precision: 0.5056 - val_recall: 0.5741 - val_auc: 0.8017 - val_prc: 0.5313
Epoch 66/200
3/3 [==============================] - 0s 20ms/step - loss: 0.5965 - tp: 456.2500 - fp: 634.5000 - tn: 2816.5000 - fn: 392.7500 - accuracy: 0.7617 - precision: 0.4197 - recall: 0.5403 - auc: 0.7605 - prc: 0.4389 - val_loss: 0.5099 - val_tp: 184.0000 - val_fp: 181.0000 - val_tn: 902.0000 - val_fn: 133.0000 - val_accuracy: 0.7757 - val_precision: 0.5041 - val_recall: 0.5804 - val_auc: 0.8026 - val_prc: 0.5350
Epoch 67/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5892 - tp: 465.7500 - fp: 609.5000 - tn: 2838.0000 - fn: 386.7500 - accuracy: 0.7669 - precision: 0.4306 - recall: 0.5413 - auc: 0.7611 - prc: 0.4669 - val_loss: 0.5111 - val_tp: 187.0000 - val_fp: 184.0000 - val_tn: 899.0000 - val_fn: 130.0000 - val_accuracy: 0.7757 - val_precision: 0.5040 - val_recall: 0.5899 - val_auc: 0.8034 - val_prc: 0.5375
Epoch 68/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5823 - tp: 482.2500 - fp: 606.5000 - tn: 2841.5000 - fn: 369.7500 - accuracy: 0.7737 - precision: 0.4431 - recall: 0.5666 - auc: 0.7735 - prc: 0.4552 - val_loss: 0.5120 - val_tp: 190.0000 - val_fp: 186.0000 - val_tn: 897.0000 - val_fn: 127.0000 - val_accuracy: 0.7764 - val_precision: 0.5053 - val_recall: 0.5994 - val_auc: 0.8038 - val_prc: 0.5395
Epoch 69/200
3/3 [==============================] - 0s 19ms/step - loss: 0.6027 - tp: 452.7500 - fp: 654.5000 - tn: 2785.2500 - fn: 407.5000 - accuracy: 0.7543 - precision: 0.4134 - recall: 0.5271 - auc: 0.7548 - prc: 0.4482 - val_loss: 0.5117 - val_tp: 191.0000 - val_fp: 188.0000 - val_tn: 895.0000 - val_fn: 126.0000 - val_accuracy: 0.7757 - val_precision: 0.5040 - val_recall: 0.6025 - val_auc: 0.8042 - val_prc: 0.5406
Epoch 70/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5996 - tp: 449.5000 - fp: 627.2500 - tn: 2825.5000 - fn: 397.7500 - accuracy: 0.7617 - precision: 0.4156 - recall: 0.5300 - auc: 0.7517 - prc: 0.4311 - val_loss: 0.5093 - val_tp: 190.0000 - val_fp: 185.0000 - val_tn: 898.0000 - val_fn: 127.0000 - val_accuracy: 0.7771 - val_precision: 0.5067 - val_recall: 0.5994 - val_auc: 0.8051 - val_prc: 0.5452
Epoch 71/200
3/3 [==============================] - 0s 20ms/step - loss: 0.5908 - tp: 454.5000 - fp: 595.5000 - tn: 2851.5000 - fn: 398.5000 - accuracy: 0.7694 - precision: 0.4347 - recall: 0.5341 - auc: 0.7638 - prc: 0.4501 - val_loss: 0.5084 - val_tp: 190.0000 - val_fp: 186.0000 - val_tn: 897.0000 - val_fn: 127.0000 - val_accuracy: 0.7764 - val_precision: 0.5053 - val_recall: 0.5994 - val_auc: 0.8055 - val_prc: 0.5464
Epoch 72/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5901 - tp: 482.2500 - fp: 607.0000 - tn: 2832.7500 - fn: 378.0000 - accuracy: 0.7708 - precision: 0.4452 - recall: 0.5625 - auc: 0.7657 - prc: 0.4681 - val_loss: 0.5081 - val_tp: 190.0000 - val_fp: 186.0000 - val_tn: 897.0000 - val_fn: 127.0000 - val_accuracy: 0.7764 - val_precision: 0.5053 - val_recall: 0.5994 - val_auc: 0.8062 - val_prc: 0.5498
Epoch 73/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5800 - tp: 493.2500 - fp: 602.5000 - tn: 2850.7500 - fn: 353.5000 - accuracy: 0.7787 - precision: 0.4503 - recall: 0.5865 - auc: 0.7740 - prc: 0.4574 - val_loss: 0.5065 - val_tp: 192.0000 - val_fp: 181.0000 - val_tn: 902.0000 - val_fn: 125.0000 - val_accuracy: 0.7814 - val_precision: 0.5147 - val_recall: 0.6057 - val_auc: 0.8072 - val_prc: 0.5529
Epoch 74/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5834 - tp: 477.0000 - fp: 582.0000 - tn: 2861.5000 - fn: 379.5000 - accuracy: 0.7773 - precision: 0.4543 - recall: 0.5583 - auc: 0.7709 - prc: 0.4788 - val_loss: 0.5051 - val_tp: 192.0000 - val_fp: 180.0000 - val_tn: 903.0000 - val_fn: 125.0000 - val_accuracy: 0.7821 - val_precision: 0.5161 - val_recall: 0.6057 - val_auc: 0.8075 - val_prc: 0.5548
Epoch 75/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5964 - tp: 465.5000 - fp: 593.2500 - tn: 2846.5000 - fn: 394.7500 - accuracy: 0.7688 - precision: 0.4400 - recall: 0.5420 - auc: 0.7665 - prc: 0.4507 - val_loss: 0.5047 - val_tp: 195.0000 - val_fp: 178.0000 - val_tn: 905.0000 - val_fn: 122.0000 - val_accuracy: 0.7857 - val_precision: 0.5228 - val_recall: 0.6151 - val_auc: 0.8087 - val_prc: 0.5583
Epoch 76/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5889 - tp: 482.2500 - fp: 607.2500 - tn: 2832.2500 - fn: 378.2500 - accuracy: 0.7711 - precision: 0.4455 - recall: 0.5630 - auc: 0.7713 - prc: 0.4680 - val_loss: 0.5047 - val_tp: 195.0000 - val_fp: 180.0000 - val_tn: 903.0000 - val_fn: 122.0000 - val_accuracy: 0.7843 - val_precision: 0.5200 - val_recall: 0.6151 - val_auc: 0.8093 - val_prc: 0.5609
Epoch 77/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5760 - tp: 470.7500 - fp: 636.5000 - tn: 2820.2500 - fn: 372.5000 - accuracy: 0.7653 - precision: 0.4217 - recall: 0.5520 - auc: 0.7730 - prc: 0.4664 - val_loss: 0.5041 - val_tp: 195.0000 - val_fp: 182.0000 - val_tn: 901.0000 - val_fn: 122.0000 - val_accuracy: 0.7829 - val_precision: 0.5172 - val_recall: 0.6151 - val_auc: 0.8101 - val_prc: 0.5630
Epoch 78/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5881 - tp: 459.7500 - fp: 636.7500 - tn: 2814.5000 - fn: 389.0000 - accuracy: 0.7621 - precision: 0.4181 - recall: 0.5438 - auc: 0.7604 - prc: 0.4617 - val_loss: 0.5036 - val_tp: 195.0000 - val_fp: 181.0000 - val_tn: 902.0000 - val_fn: 122.0000 - val_accuracy: 0.7836 - val_precision: 0.5186 - val_recall: 0.6151 - val_auc: 0.8107 - val_prc: 0.5660
Epoch 79/200
3/3 [==============================] - 0s 20ms/step - loss: 0.5819 - tp: 465.7500 - fp: 606.0000 - tn: 2841.0000 - fn: 387.2500 - accuracy: 0.7701 - precision: 0.4371 - recall: 0.5465 - auc: 0.7774 - prc: 0.4690 - val_loss: 0.5019 - val_tp: 195.0000 - val_fp: 181.0000 - val_tn: 902.0000 - val_fn: 122.0000 - val_accuracy: 0.7836 - val_precision: 0.5186 - val_recall: 0.6151 - val_auc: 0.8116 - val_prc: 0.5686
Epoch 80/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5836 - tp: 471.5000 - fp: 601.0000 - tn: 2847.0000 - fn: 380.5000 - accuracy: 0.7728 - precision: 0.4420 - recall: 0.5555 - auc: 0.7726 - prc: 0.4674 - val_loss: 0.5006 - val_tp: 196.0000 - val_fp: 181.0000 - val_tn: 902.0000 - val_fn: 121.0000 - val_accuracy: 0.7843 - val_precision: 0.5199 - val_recall: 0.6183 - val_auc: 0.8123 - val_prc: 0.5722
Epoch 81/200
3/3 [==============================] - 0s 20ms/step - loss: 0.5809 - tp: 487.0000 - fp: 572.7500 - tn: 2865.5000 - fn: 374.7500 - accuracy: 0.7792 - precision: 0.4630 - recall: 0.5649 - auc: 0.7765 - prc: 0.4918 - val_loss: 0.5002 - val_tp: 197.0000 - val_fp: 181.0000 - val_tn: 902.0000 - val_fn: 120.0000 - val_accuracy: 0.7850 - val_precision: 0.5212 - val_recall: 0.6215 - val_auc: 0.8126 - val_prc: 0.5726
Epoch 82/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5785 - tp: 490.2500 - fp: 577.0000 - tn: 2867.7500 - fn: 365.0000 - accuracy: 0.7800 - precision: 0.4590 - recall: 0.5718 - auc: 0.7779 - prc: 0.4772 - val_loss: 0.5003 - val_tp: 197.0000 - val_fp: 182.0000 - val_tn: 901.0000 - val_fn: 120.0000 - val_accuracy: 0.7843 - val_precision: 0.5198 - val_recall: 0.6215 - val_auc: 0.8132 - val_prc: 0.5743
Epoch 83/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5831 - tp: 465.0000 - fp: 596.7500 - tn: 2840.7500 - fn: 397.5000 - accuracy: 0.7682 - precision: 0.4402 - recall: 0.5371 - auc: 0.7776 - prc: 0.4863 - val_loss: 0.5018 - val_tp: 198.0000 - val_fp: 186.0000 - val_tn: 897.0000 - val_fn: 119.0000 - val_accuracy: 0.7821 - val_precision: 0.5156 - val_recall: 0.6246 - val_auc: 0.8136 - val_prc: 0.5762
Epoch 84/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5715 - tp: 474.0000 - fp: 608.0000 - tn: 2840.2500 - fn: 377.7500 - accuracy: 0.7720 - precision: 0.4416 - recall: 0.5576 - auc: 0.7839 - prc: 0.4883 - val_loss: 0.5017 - val_tp: 199.0000 - val_fp: 184.0000 - val_tn: 899.0000 - val_fn: 118.0000 - val_accuracy: 0.7843 - val_precision: 0.5196 - val_recall: 0.6278 - val_auc: 0.8142 - val_prc: 0.5771
Epoch 85/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5672 - tp: 493.7500 - fp: 611.5000 - tn: 2840.7500 - fn: 354.0000 - accuracy: 0.7738 - precision: 0.4421 - recall: 0.5803 - auc: 0.7845 - prc: 0.5002 - val_loss: 0.4995 - val_tp: 199.0000 - val_fp: 179.0000 - val_tn: 904.0000 - val_fn: 118.0000 - val_accuracy: 0.7879 - val_precision: 0.5265 - val_recall: 0.6278 - val_auc: 0.8144 - val_prc: 0.5803
Epoch 86/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5772 - tp: 475.7500 - fp: 590.7500 - tn: 2862.7500 - fn: 370.7500 - accuracy: 0.7773 - precision: 0.4463 - recall: 0.5609 - auc: 0.7751 - prc: 0.4783 - val_loss: 0.4982 - val_tp: 201.0000 - val_fp: 178.0000 - val_tn: 905.0000 - val_fn: 116.0000 - val_accuracy: 0.7900 - val_precision: 0.5303 - val_recall: 0.6341 - val_auc: 0.8151 - val_prc: 0.5826
Epoch 87/200
3/3 [==============================] - 0s 20ms/step - loss: 0.5771 - tp: 464.5000 - fp: 573.5000 - tn: 2869.5000 - fn: 392.5000 - accuracy: 0.7747 - precision: 0.4486 - recall: 0.5426 - auc: 0.7791 - prc: 0.4885 - val_loss: 0.4969 - val_tp: 202.0000 - val_fp: 177.0000 - val_tn: 906.0000 - val_fn: 115.0000 - val_accuracy: 0.7914 - val_precision: 0.5330 - val_recall: 0.6372 - val_auc: 0.8152 - val_prc: 0.5839
Epoch 88/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5828 - tp: 468.2500 - fp: 602.0000 - tn: 2843.0000 - fn: 386.7500 - accuracy: 0.7689 - precision: 0.4371 - recall: 0.5470 - auc: 0.7747 - prc: 0.4771 - val_loss: 0.4953 - val_tp: 202.0000 - val_fp: 177.0000 - val_tn: 906.0000 - val_fn: 115.0000 - val_accuracy: 0.7914 - val_precision: 0.5330 - val_recall: 0.6372 - val_auc: 0.8159 - val_prc: 0.5868
Epoch 89/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5617 - tp: 471.0000 - fp: 586.7500 - tn: 2872.5000 - fn: 369.7500 - accuracy: 0.7804 - precision: 0.4484 - recall: 0.5646 - auc: 0.7829 - prc: 0.4962 - val_loss: 0.4942 - val_tp: 201.0000 - val_fp: 177.0000 - val_tn: 906.0000 - val_fn: 116.0000 - val_accuracy: 0.7907 - val_precision: 0.5317 - val_recall: 0.6341 - val_auc: 0.8163 - val_prc: 0.5884
Epoch 90/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5625 - tp: 501.2500 - fp: 577.2500 - tn: 2862.7500 - fn: 358.7500 - accuracy: 0.7856 - precision: 0.4720 - recall: 0.5901 - auc: 0.7961 - prc: 0.5086 - val_loss: 0.4941 - val_tp: 202.0000 - val_fp: 179.0000 - val_tn: 904.0000 - val_fn: 115.0000 - val_accuracy: 0.7900 - val_precision: 0.5302 - val_recall: 0.6372 - val_auc: 0.8166 - val_prc: 0.5896
Epoch 91/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5839 - tp: 473.5000 - fp: 612.5000 - tn: 2843.7500 - fn: 370.2500 - accuracy: 0.7697 - precision: 0.4297 - recall: 0.5565 - auc: 0.7665 - prc: 0.4633 - val_loss: 0.4926 - val_tp: 201.0000 - val_fp: 178.0000 - val_tn: 905.0000 - val_fn: 116.0000 - val_accuracy: 0.7900 - val_precision: 0.5303 - val_recall: 0.6341 - val_auc: 0.8171 - val_prc: 0.5917
Epoch 92/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5689 - tp: 485.2500 - fp: 585.7500 - tn: 2866.7500 - fn: 362.2500 - accuracy: 0.7785 - precision: 0.4490 - recall: 0.5682 - auc: 0.7819 - prc: 0.4912 - val_loss: 0.4925 - val_tp: 200.0000 - val_fp: 178.0000 - val_tn: 905.0000 - val_fn: 117.0000 - val_accuracy: 0.7893 - val_precision: 0.5291 - val_recall: 0.6309 - val_auc: 0.8169 - val_prc: 0.5928
Epoch 93/200
3/3 [==============================] - 0s 20ms/step - loss: 0.5752 - tp: 481.5000 - fp: 540.7500 - tn: 2896.0000 - fn: 381.7500 - accuracy: 0.7837 - precision: 0.4706 - recall: 0.5544 - auc: 0.7855 - prc: 0.5043 - val_loss: 0.4944 - val_tp: 203.0000 - val_fp: 179.0000 - val_tn: 904.0000 - val_fn: 114.0000 - val_accuracy: 0.7907 - val_precision: 0.5314 - val_recall: 0.6404 - val_auc: 0.8174 - val_prc: 0.5929
Epoch 94/200
3/3 [==============================] - 0s 20ms/step - loss: 0.5534 - tp: 476.0000 - fp: 576.7500 - tn: 2883.0000 - fn: 364.2500 - accuracy: 0.7848 - precision: 0.4556 - recall: 0.5713 - auc: 0.7960 - prc: 0.5108 - val_loss: 0.4957 - val_tp: 207.0000 - val_fp: 181.0000 - val_tn: 902.0000 - val_fn: 110.0000 - val_accuracy: 0.7921 - val_precision: 0.5335 - val_recall: 0.6530 - val_auc: 0.8180 - val_prc: 0.5949
Epoch 95/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5609 - tp: 488.0000 - fp: 599.7500 - tn: 2848.7500 - fn: 363.5000 - accuracy: 0.7762 - precision: 0.4477 - recall: 0.5752 - auc: 0.7848 - prc: 0.5206 - val_loss: 0.4956 - val_tp: 209.0000 - val_fp: 182.0000 - val_tn: 901.0000 - val_fn: 108.0000 - val_accuracy: 0.7929 - val_precision: 0.5345 - val_recall: 0.6593 - val_auc: 0.8186 - val_prc: 0.5970
Epoch 96/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5653 - tp: 504.0000 - fp: 608.2500 - tn: 2842.0000 - fn: 345.7500 - accuracy: 0.7760 - precision: 0.4502 - recall: 0.5933 - auc: 0.7871 - prc: 0.4948 - val_loss: 0.4942 - val_tp: 210.0000 - val_fp: 182.0000 - val_tn: 901.0000 - val_fn: 107.0000 - val_accuracy: 0.7936 - val_precision: 0.5357 - val_recall: 0.6625 - val_auc: 0.8194 - val_prc: 0.5992
Epoch 97/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5512 - tp: 501.0000 - fp: 576.7500 - tn: 2880.0000 - fn: 342.2500 - accuracy: 0.7889 - precision: 0.4669 - recall: 0.5984 - auc: 0.7929 - prc: 0.5110 - val_loss: 0.4931 - val_tp: 212.0000 - val_fp: 182.0000 - val_tn: 901.0000 - val_fn: 105.0000 - val_accuracy: 0.7950 - val_precision: 0.5381 - val_recall: 0.6688 - val_auc: 0.8202 - val_prc: 0.6011
Epoch 98/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5673 - tp: 514.0000 - fp: 607.2500 - tn: 2836.5000 - fn: 342.2500 - accuracy: 0.7789 - precision: 0.4592 - recall: 0.5996 - auc: 0.7875 - prc: 0.4977 - val_loss: 0.4909 - val_tp: 210.0000 - val_fp: 182.0000 - val_tn: 901.0000 - val_fn: 107.0000 - val_accuracy: 0.7936 - val_precision: 0.5357 - val_recall: 0.6625 - val_auc: 0.8211 - val_prc: 0.6035
Epoch 99/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5649 - tp: 497.2500 - fp: 600.7500 - tn: 2848.0000 - fn: 354.0000 - accuracy: 0.7776 - precision: 0.4527 - recall: 0.5856 - auc: 0.7918 - prc: 0.4976 - val_loss: 0.4880 - val_tp: 206.0000 - val_fp: 179.0000 - val_tn: 904.0000 - val_fn: 111.0000 - val_accuracy: 0.7929 - val_precision: 0.5351 - val_recall: 0.6498 - val_auc: 0.8218 - val_prc: 0.6067
Epoch 100/200
3/3 [==============================] - 0s 20ms/step - loss: 0.5650 - tp: 497.2500 - fp: 569.7500 - tn: 2874.2500 - fn: 358.7500 - accuracy: 0.7852 - precision: 0.4698 - recall: 0.5828 - auc: 0.7890 - prc: 0.5033 - val_loss: 0.4864 - val_tp: 205.0000 - val_fp: 179.0000 - val_tn: 904.0000 - val_fn: 112.0000 - val_accuracy: 0.7921 - val_precision: 0.5339 - val_recall: 0.6467 - val_auc: 0.8226 - val_prc: 0.6104
Epoch 101/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5647 - tp: 477.7500 - fp: 582.5000 - tn: 2864.0000 - fn: 375.7500 - accuracy: 0.7763 - precision: 0.4464 - recall: 0.5572 - auc: 0.7909 - prc: 0.4893 - val_loss: 0.4859 - val_tp: 206.0000 - val_fp: 178.0000 - val_tn: 905.0000 - val_fn: 111.0000 - val_accuracy: 0.7936 - val_precision: 0.5365 - val_recall: 0.6498 - val_auc: 0.8231 - val_prc: 0.6124
Epoch 102/200
3/3 [==============================] - 0s 21ms/step - loss: 0.5579 - tp: 493.7500 - fp: 555.0000 - tn: 2895.7500 - fn: 355.5000 - accuracy: 0.7905 - precision: 0.4755 - recall: 0.5836 - auc: 0.7952 - prc: 0.5076 - val_loss: 0.4862 - val_tp: 206.0000 - val_fp: 179.0000 - val_tn: 904.0000 - val_fn: 111.0000 - val_accuracy: 0.7929 - val_precision: 0.5351 - val_recall: 0.6498 - val_auc: 0.8243 - val_prc: 0.6154
Epoch 103/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5596 - tp: 503.0000 - fp: 601.7500 - tn: 2848.7500 - fn: 346.5000 - accuracy: 0.7798 - precision: 0.4559 - recall: 0.6017 - auc: 0.7905 - prc: 0.5106 - val_loss: 0.4864 - val_tp: 207.0000 - val_fp: 178.0000 - val_tn: 905.0000 - val_fn: 110.0000 - val_accuracy: 0.7943 - val_precision: 0.5377 - val_recall: 0.6530 - val_auc: 0.8244 - val_prc: 0.6164
Epoch 104/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5437 - tp: 506.2500 - fp: 576.0000 - tn: 2877.0000 - fn: 340.7500 - accuracy: 0.7890 - precision: 0.4701 - recall: 0.5986 - auc: 0.7980 - prc: 0.5319 - val_loss: 0.4867 - val_tp: 208.0000 - val_fp: 179.0000 - val_tn: 904.0000 - val_fn: 109.0000 - val_accuracy: 0.7943 - val_precision: 0.5375 - val_recall: 0.6562 - val_auc: 0.8249 - val_prc: 0.6178
Epoch 105/200
3/3 [==============================] - 0s 20ms/step - loss: 0.5660 - tp: 517.5000 - fp: 622.2500 - tn: 2814.7500 - fn: 345.5000 - accuracy: 0.7751 - precision: 0.4583 - recall: 0.6003 - auc: 0.7910 - prc: 0.5085 - val_loss: 0.4872 - val_tp: 210.0000 - val_fp: 181.0000 - val_tn: 902.0000 - val_fn: 107.0000 - val_accuracy: 0.7943 - val_precision: 0.5371 - val_recall: 0.6625 - val_auc: 0.8250 - val_prc: 0.6184
Epoch 106/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5590 - tp: 511.2500 - fp: 626.2500 - tn: 2825.0000 - fn: 337.5000 - accuracy: 0.7751 - precision: 0.4490 - recall: 0.6032 - auc: 0.7945 - prc: 0.5003 - val_loss: 0.4854 - val_tp: 210.0000 - val_fp: 178.0000 - val_tn: 905.0000 - val_fn: 107.0000 - val_accuracy: 0.7964 - val_precision: 0.5412 - val_recall: 0.6625 - val_auc: 0.8256 - val_prc: 0.6199
Epoch 107/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5545 - tp: 505.5000 - fp: 589.0000 - tn: 2855.5000 - fn: 350.0000 - accuracy: 0.7814 - precision: 0.4636 - recall: 0.5940 - auc: 0.7975 - prc: 0.5278 - val_loss: 0.4840 - val_tp: 210.0000 - val_fp: 176.0000 - val_tn: 907.0000 - val_fn: 107.0000 - val_accuracy: 0.7979 - val_precision: 0.5440 - val_recall: 0.6625 - val_auc: 0.8258 - val_prc: 0.6210
Epoch 108/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5683 - tp: 486.0000 - fp: 581.2500 - tn: 2863.5000 - fn: 369.2500 - accuracy: 0.7797 - precision: 0.4579 - recall: 0.5678 - auc: 0.7864 - prc: 0.5037 - val_loss: 0.4839 - val_tp: 210.0000 - val_fp: 179.0000 - val_tn: 904.0000 - val_fn: 107.0000 - val_accuracy: 0.7957 - val_precision: 0.5398 - val_recall: 0.6625 - val_auc: 0.8264 - val_prc: 0.6227
Epoch 109/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5618 - tp: 528.0000 - fp: 576.5000 - tn: 2855.0000 - fn: 340.5000 - accuracy: 0.7865 - precision: 0.4841 - recall: 0.6056 - auc: 0.7987 - prc: 0.5216 - val_loss: 0.4843 - val_tp: 210.0000 - val_fp: 183.0000 - val_tn: 900.0000 - val_fn: 107.0000 - val_accuracy: 0.7929 - val_precision: 0.5344 - val_recall: 0.6625 - val_auc: 0.8263 - val_prc: 0.6240
Epoch 110/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5549 - tp: 505.5000 - fp: 582.5000 - tn: 2855.7500 - fn: 356.2500 - accuracy: 0.7823 - precision: 0.4685 - recall: 0.5873 - auc: 0.8020 - prc: 0.5305 - val_loss: 0.4842 - val_tp: 209.0000 - val_fp: 183.0000 - val_tn: 900.0000 - val_fn: 108.0000 - val_accuracy: 0.7921 - val_precision: 0.5332 - val_recall: 0.6593 - val_auc: 0.8269 - val_prc: 0.6254
Epoch 111/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5494 - tp: 531.0000 - fp: 588.2500 - tn: 2852.2500 - fn: 328.5000 - accuracy: 0.7881 - precision: 0.4769 - recall: 0.6180 - auc: 0.8004 - prc: 0.5369 - val_loss: 0.4852 - val_tp: 209.0000 - val_fp: 184.0000 - val_tn: 899.0000 - val_fn: 108.0000 - val_accuracy: 0.7914 - val_precision: 0.5318 - val_recall: 0.6593 - val_auc: 0.8270 - val_prc: 0.6256
Epoch 112/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5561 - tp: 518.2500 - fp: 567.2500 - tn: 2871.5000 - fn: 343.0000 - accuracy: 0.7886 - precision: 0.4812 - recall: 0.6025 - auc: 0.8037 - prc: 0.5200 - val_loss: 0.4854 - val_tp: 209.0000 - val_fp: 184.0000 - val_tn: 899.0000 - val_fn: 108.0000 - val_accuracy: 0.7914 - val_precision: 0.5318 - val_recall: 0.6593 - val_auc: 0.8277 - val_prc: 0.6285
Epoch 113/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5488 - tp: 509.0000 - fp: 573.7500 - tn: 2885.5000 - fn: 331.7500 - accuracy: 0.7901 - precision: 0.4692 - recall: 0.6045 - auc: 0.7970 - prc: 0.5162 - val_loss: 0.4837 - val_tp: 209.0000 - val_fp: 184.0000 - val_tn: 899.0000 - val_fn: 108.0000 - val_accuracy: 0.7914 - val_precision: 0.5318 - val_recall: 0.6593 - val_auc: 0.8281 - val_prc: 0.6298
Epoch 114/200
3/3 [==============================] - 0s 20ms/step - loss: 0.5427 - tp: 503.2500 - fp: 587.5000 - tn: 2865.2500 - fn: 344.0000 - accuracy: 0.7818 - precision: 0.4554 - recall: 0.5893 - auc: 0.8009 - prc: 0.5305 - val_loss: 0.4824 - val_tp: 209.0000 - val_fp: 183.0000 - val_tn: 900.0000 - val_fn: 108.0000 - val_accuracy: 0.7921 - val_precision: 0.5332 - val_recall: 0.6593 - val_auc: 0.8287 - val_prc: 0.6323
Epoch 115/200
3/3 [==============================] - 0s 21ms/step - loss: 0.5392 - tp: 520.0000 - fp: 566.2500 - tn: 2887.7500 - fn: 326.0000 - accuracy: 0.7929 - precision: 0.4790 - recall: 0.6159 - auc: 0.8061 - prc: 0.5530 - val_loss: 0.4820 - val_tp: 209.0000 - val_fp: 183.0000 - val_tn: 900.0000 - val_fn: 108.0000 - val_accuracy: 0.7921 - val_precision: 0.5332 - val_recall: 0.6593 - val_auc: 0.8291 - val_prc: 0.6320
Epoch 116/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5299 - tp: 529.2500 - fp: 578.2500 - tn: 2876.5000 - fn: 316.0000 - accuracy: 0.7913 - precision: 0.4749 - recall: 0.6254 - auc: 0.8126 - prc: 0.5611 - val_loss: 0.4819 - val_tp: 210.0000 - val_fp: 182.0000 - val_tn: 901.0000 - val_fn: 107.0000 - val_accuracy: 0.7936 - val_precision: 0.5357 - val_recall: 0.6625 - val_auc: 0.8295 - val_prc: 0.6341
Epoch 117/200
3/3 [==============================] - 0s 20ms/step - loss: 0.5559 - tp: 498.0000 - fp: 606.5000 - tn: 2841.5000 - fn: 354.0000 - accuracy: 0.7767 - precision: 0.4516 - recall: 0.5870 - auc: 0.7979 - prc: 0.5142 - val_loss: 0.4809 - val_tp: 209.0000 - val_fp: 180.0000 - val_tn: 903.0000 - val_fn: 108.0000 - val_accuracy: 0.7943 - val_precision: 0.5373 - val_recall: 0.6593 - val_auc: 0.8304 - val_prc: 0.6351
Epoch 118/200
3/3 [==============================] - 0s 21ms/step - loss: 0.5491 - tp: 498.2500 - fp: 579.5000 - tn: 2880.2500 - fn: 342.0000 - accuracy: 0.7851 - precision: 0.4575 - recall: 0.5894 - auc: 0.7972 - prc: 0.5118 - val_loss: 0.4787 - val_tp: 209.0000 - val_fp: 180.0000 - val_tn: 903.0000 - val_fn: 108.0000 - val_accuracy: 0.7943 - val_precision: 0.5373 - val_recall: 0.6593 - val_auc: 0.8308 - val_prc: 0.6358
Epoch 119/200
3/3 [==============================] - 0s 22ms/step - loss: 0.5630 - tp: 499.5000 - fp: 578.5000 - tn: 2859.5000 - fn: 362.5000 - accuracy: 0.7814 - precision: 0.4673 - recall: 0.5762 - auc: 0.7958 - prc: 0.5223 - val_loss: 0.4783 - val_tp: 209.0000 - val_fp: 176.0000 - val_tn: 907.0000 - val_fn: 108.0000 - val_accuracy: 0.7971 - val_precision: 0.5429 - val_recall: 0.6593 - val_auc: 0.8312 - val_prc: 0.6364
Epoch 120/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5550 - tp: 502.7500 - fp: 595.5000 - tn: 2853.2500 - fn: 348.5000 - accuracy: 0.7796 - precision: 0.4565 - recall: 0.5838 - auc: 0.7936 - prc: 0.5333 - val_loss: 0.4760 - val_tp: 209.0000 - val_fp: 173.0000 - val_tn: 910.0000 - val_fn: 108.0000 - val_accuracy: 0.7993 - val_precision: 0.5471 - val_recall: 0.6593 - val_auc: 0.8319 - val_prc: 0.6371
Epoch 121/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5431 - tp: 499.7500 - fp: 543.5000 - tn: 2915.5000 - fn: 341.2500 - accuracy: 0.7929 - precision: 0.4711 - recall: 0.5899 - auc: 0.8040 - prc: 0.5231 - val_loss: 0.4746 - val_tp: 210.0000 - val_fp: 173.0000 - val_tn: 910.0000 - val_fn: 107.0000 - val_accuracy: 0.8000 - val_precision: 0.5483 - val_recall: 0.6625 - val_auc: 0.8325 - val_prc: 0.6393
Epoch 122/200
3/3 [==============================] - 0s 21ms/step - loss: 0.5476 - tp: 517.7500 - fp: 577.2500 - tn: 2862.7500 - fn: 342.2500 - accuracy: 0.7857 - precision: 0.4764 - recall: 0.6045 - auc: 0.8107 - prc: 0.5333 - val_loss: 0.4747 - val_tp: 211.0000 - val_fp: 174.0000 - val_tn: 909.0000 - val_fn: 106.0000 - val_accuracy: 0.8000 - val_precision: 0.5481 - val_recall: 0.6656 - val_auc: 0.8327 - val_prc: 0.6413
Epoch 123/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5447 - tp: 512.0000 - fp: 552.7500 - tn: 2902.0000 - fn: 333.2500 - accuracy: 0.7947 - precision: 0.4796 - recall: 0.6054 - auc: 0.8043 - prc: 0.5190 - val_loss: 0.4747 - val_tp: 211.0000 - val_fp: 173.0000 - val_tn: 910.0000 - val_fn: 106.0000 - val_accuracy: 0.8007 - val_precision: 0.5495 - val_recall: 0.6656 - val_auc: 0.8332 - val_prc: 0.6429
Epoch 124/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5338 - tp: 518.2500 - fp: 551.0000 - tn: 2905.5000 - fn: 325.2500 - accuracy: 0.7973 - precision: 0.4845 - recall: 0.6158 - auc: 0.8126 - prc: 0.5330 - val_loss: 0.4757 - val_tp: 211.0000 - val_fp: 176.0000 - val_tn: 907.0000 - val_fn: 106.0000 - val_accuracy: 0.7986 - val_precision: 0.5452 - val_recall: 0.6656 - val_auc: 0.8334 - val_prc: 0.6427
Epoch 125/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5432 - tp: 513.0000 - fp: 583.2500 - tn: 2869.7500 - fn: 334.0000 - accuracy: 0.7838 - precision: 0.4618 - recall: 0.6007 - auc: 0.8034 - prc: 0.5294 - val_loss: 0.4769 - val_tp: 212.0000 - val_fp: 179.0000 - val_tn: 904.0000 - val_fn: 105.0000 - val_accuracy: 0.7971 - val_precision: 0.5422 - val_recall: 0.6688 - val_auc: 0.8339 - val_prc: 0.6448
Epoch 126/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5483 - tp: 508.0000 - fp: 605.7500 - tn: 2845.5000 - fn: 340.7500 - accuracy: 0.7799 - precision: 0.4563 - recall: 0.5970 - auc: 0.8005 - prc: 0.5313 - val_loss: 0.4780 - val_tp: 213.0000 - val_fp: 185.0000 - val_tn: 898.0000 - val_fn: 104.0000 - val_accuracy: 0.7936 - val_precision: 0.5352 - val_recall: 0.6719 - val_auc: 0.8338 - val_prc: 0.6452
Epoch 127/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5446 - tp: 524.0000 - fp: 577.0000 - tn: 2866.5000 - fn: 332.5000 - accuracy: 0.7882 - precision: 0.4787 - recall: 0.6108 - auc: 0.8065 - prc: 0.5480 - val_loss: 0.4781 - val_tp: 213.0000 - val_fp: 184.0000 - val_tn: 899.0000 - val_fn: 104.0000 - val_accuracy: 0.7943 - val_precision: 0.5365 - val_recall: 0.6719 - val_auc: 0.8341 - val_prc: 0.6461
Epoch 128/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5524 - tp: 532.7500 - fp: 587.2500 - tn: 2848.5000 - fn: 331.5000 - accuracy: 0.7865 - precision: 0.4794 - recall: 0.6175 - auc: 0.8070 - prc: 0.5347 - val_loss: 0.4772 - val_tp: 213.0000 - val_fp: 185.0000 - val_tn: 898.0000 - val_fn: 104.0000 - val_accuracy: 0.7936 - val_precision: 0.5352 - val_recall: 0.6719 - val_auc: 0.8341 - val_prc: 0.6469
Epoch 129/200
3/3 [==============================] - 0s 21ms/step - loss: 0.5368 - tp: 535.2500 - fp: 593.2500 - tn: 2858.5000 - fn: 313.0000 - accuracy: 0.7889 - precision: 0.4736 - recall: 0.6348 - auc: 0.8112 - prc: 0.5405 - val_loss: 0.4740 - val_tp: 213.0000 - val_fp: 178.0000 - val_tn: 905.0000 - val_fn: 104.0000 - val_accuracy: 0.7986 - val_precision: 0.5448 - val_recall: 0.6719 - val_auc: 0.8345 - val_prc: 0.6483
Epoch 130/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5346 - tp: 519.5000 - fp: 552.7500 - tn: 2899.7500 - fn: 328.0000 - accuracy: 0.7964 - precision: 0.4860 - recall: 0.6129 - auc: 0.8115 - prc: 0.5463 - val_loss: 0.4718 - val_tp: 212.0000 - val_fp: 175.0000 - val_tn: 908.0000 - val_fn: 105.0000 - val_accuracy: 0.8000 - val_precision: 0.5478 - val_recall: 0.6688 - val_auc: 0.8351 - val_prc: 0.6499
Epoch 131/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5475 - tp: 511.5000 - fp: 602.0000 - tn: 2845.2500 - fn: 341.2500 - accuracy: 0.7807 - precision: 0.4582 - recall: 0.5975 - auc: 0.8018 - prc: 0.5358 - val_loss: 0.4700 - val_tp: 211.0000 - val_fp: 171.0000 - val_tn: 912.0000 - val_fn: 106.0000 - val_accuracy: 0.8021 - val_precision: 0.5524 - val_recall: 0.6656 - val_auc: 0.8350 - val_prc: 0.6496
Epoch 132/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5498 - tp: 505.2500 - fp: 577.7500 - tn: 2869.7500 - fn: 347.2500 - accuracy: 0.7830 - precision: 0.4635 - recall: 0.5867 - auc: 0.8039 - prc: 0.5295 - val_loss: 0.4681 - val_tp: 210.0000 - val_fp: 170.0000 - val_tn: 913.0000 - val_fn: 107.0000 - val_accuracy: 0.8021 - val_precision: 0.5526 - val_recall: 0.6625 - val_auc: 0.8351 - val_prc: 0.6492
Epoch 133/200
3/3 [==============================] - 0s 20ms/step - loss: 0.5357 - tp: 496.0000 - fp: 547.0000 - tn: 2904.0000 - fn: 353.0000 - accuracy: 0.7917 - precision: 0.4743 - recall: 0.5810 - auc: 0.8081 - prc: 0.5559 - val_loss: 0.4672 - val_tp: 209.0000 - val_fp: 166.0000 - val_tn: 917.0000 - val_fn: 108.0000 - val_accuracy: 0.8043 - val_precision: 0.5573 - val_recall: 0.6593 - val_auc: 0.8350 - val_prc: 0.6480
Epoch 134/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5394 - tp: 518.0000 - fp: 549.2500 - tn: 2898.2500 - fn: 334.5000 - accuracy: 0.7938 - precision: 0.4851 - recall: 0.6082 - auc: 0.8083 - prc: 0.5521 - val_loss: 0.4677 - val_tp: 211.0000 - val_fp: 170.0000 - val_tn: 913.0000 - val_fn: 106.0000 - val_accuracy: 0.8029 - val_precision: 0.5538 - val_recall: 0.6656 - val_auc: 0.8352 - val_prc: 0.6479
Epoch 135/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5392 - tp: 533.2500 - fp: 567.2500 - tn: 2878.2500 - fn: 321.2500 - accuracy: 0.7943 - precision: 0.4875 - recall: 0.6256 - auc: 0.8120 - prc: 0.5509 - val_loss: 0.4689 - val_tp: 211.0000 - val_fp: 171.0000 - val_tn: 912.0000 - val_fn: 106.0000 - val_accuracy: 0.8021 - val_precision: 0.5524 - val_recall: 0.6656 - val_auc: 0.8352 - val_prc: 0.6469
Epoch 136/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5444 - tp: 498.7500 - fp: 576.2500 - tn: 2873.7500 - fn: 351.2500 - accuracy: 0.7844 - precision: 0.4636 - recall: 0.5860 - auc: 0.8061 - prc: 0.5333 - val_loss: 0.4699 - val_tp: 211.0000 - val_fp: 171.0000 - val_tn: 912.0000 - val_fn: 106.0000 - val_accuracy: 0.8021 - val_precision: 0.5524 - val_recall: 0.6656 - val_auc: 0.8354 - val_prc: 0.6479
Epoch 137/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5382 - tp: 521.2500 - fp: 581.2500 - tn: 2870.0000 - fn: 327.5000 - accuracy: 0.7911 - precision: 0.4762 - recall: 0.6184 - auc: 0.8125 - prc: 0.5409 - val_loss: 0.4710 - val_tp: 212.0000 - val_fp: 173.0000 - val_tn: 910.0000 - val_fn: 105.0000 - val_accuracy: 0.8014 - val_precision: 0.5506 - val_recall: 0.6688 - val_auc: 0.8356 - val_prc: 0.6484
Epoch 138/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5386 - tp: 535.5000 - fp: 568.0000 - tn: 2875.2500 - fn: 321.2500 - accuracy: 0.7946 - precision: 0.4901 - recall: 0.6288 - auc: 0.8169 - prc: 0.5394 - val_loss: 0.4720 - val_tp: 212.0000 - val_fp: 175.0000 - val_tn: 908.0000 - val_fn: 105.0000 - val_accuracy: 0.8000 - val_precision: 0.5478 - val_recall: 0.6688 - val_auc: 0.8358 - val_prc: 0.6490
Epoch 139/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5470 - tp: 516.7500 - fp: 560.7500 - tn: 2879.2500 - fn: 343.2500 - accuracy: 0.7900 - precision: 0.4814 - recall: 0.6011 - auc: 0.8089 - prc: 0.5485 - val_loss: 0.4732 - val_tp: 212.0000 - val_fp: 180.0000 - val_tn: 903.0000 - val_fn: 105.0000 - val_accuracy: 0.7964 - val_precision: 0.5408 - val_recall: 0.6688 - val_auc: 0.8362 - val_prc: 0.6503
Epoch 140/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5376 - tp: 524.5000 - fp: 582.5000 - tn: 2868.2500 - fn: 324.7500 - accuracy: 0.7891 - precision: 0.4742 - recall: 0.6184 - auc: 0.8135 - prc: 0.5474 - val_loss: 0.4720 - val_tp: 213.0000 - val_fp: 178.0000 - val_tn: 905.0000 - val_fn: 104.0000 - val_accuracy: 0.7986 - val_precision: 0.5448 - val_recall: 0.6719 - val_auc: 0.8368 - val_prc: 0.6534
Epoch 141/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5332 - tp: 532.2500 - fp: 545.0000 - tn: 2906.7500 - fn: 316.0000 - accuracy: 0.8007 - precision: 0.4951 - recall: 0.6282 - auc: 0.8114 - prc: 0.5540 - val_loss: 0.4714 - val_tp: 212.0000 - val_fp: 176.0000 - val_tn: 907.0000 - val_fn: 105.0000 - val_accuracy: 0.7993 - val_precision: 0.5464 - val_recall: 0.6688 - val_auc: 0.8373 - val_prc: 0.6551
Epoch 142/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5444 - tp: 523.7500 - fp: 569.5000 - tn: 2879.5000 - fn: 327.2500 - accuracy: 0.7898 - precision: 0.4756 - recall: 0.6127 - auc: 0.8031 - prc: 0.5465 - val_loss: 0.4708 - val_tp: 212.0000 - val_fp: 175.0000 - val_tn: 908.0000 - val_fn: 105.0000 - val_accuracy: 0.8000 - val_precision: 0.5478 - val_recall: 0.6688 - val_auc: 0.8374 - val_prc: 0.6562
Epoch 143/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5463 - tp: 516.0000 - fp: 562.7500 - tn: 2890.5000 - fn: 330.7500 - accuracy: 0.7908 - precision: 0.4745 - recall: 0.6085 - auc: 0.8044 - prc: 0.5262 - val_loss: 0.4709 - val_tp: 210.0000 - val_fp: 173.0000 - val_tn: 910.0000 - val_fn: 107.0000 - val_accuracy: 0.8000 - val_precision: 0.5483 - val_recall: 0.6625 - val_auc: 0.8380 - val_prc: 0.6583
Epoch 144/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5364 - tp: 511.5000 - fp: 560.2500 - tn: 2889.5000 - fn: 338.7500 - accuracy: 0.7900 - precision: 0.4746 - recall: 0.5981 - auc: 0.8133 - prc: 0.5396 - val_loss: 0.4717 - val_tp: 212.0000 - val_fp: 174.0000 - val_tn: 909.0000 - val_fn: 105.0000 - val_accuracy: 0.8007 - val_precision: 0.5492 - val_recall: 0.6688 - val_auc: 0.8375 - val_prc: 0.6590
Epoch 145/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5467 - tp: 518.2500 - fp: 582.0000 - tn: 2855.0000 - fn: 344.7500 - accuracy: 0.7843 - precision: 0.4747 - recall: 0.5998 - auc: 0.8092 - prc: 0.5446 - val_loss: 0.4707 - val_tp: 212.0000 - val_fp: 177.0000 - val_tn: 906.0000 - val_fn: 105.0000 - val_accuracy: 0.7986 - val_precision: 0.5450 - val_recall: 0.6688 - val_auc: 0.8375 - val_prc: 0.6599
Epoch 146/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5434 - tp: 522.7500 - fp: 574.0000 - tn: 2878.0000 - fn: 325.2500 - accuracy: 0.7904 - precision: 0.4742 - recall: 0.6208 - auc: 0.8051 - prc: 0.5285 - val_loss: 0.4681 - val_tp: 210.0000 - val_fp: 175.0000 - val_tn: 908.0000 - val_fn: 107.0000 - val_accuracy: 0.7986 - val_precision: 0.5455 - val_recall: 0.6625 - val_auc: 0.8380 - val_prc: 0.6606
Epoch 147/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5450 - tp: 520.5000 - fp: 567.5000 - tn: 2881.5000 - fn: 330.5000 - accuracy: 0.7907 - precision: 0.4753 - recall: 0.6095 - auc: 0.8055 - prc: 0.5264 - val_loss: 0.4654 - val_tp: 208.0000 - val_fp: 172.0000 - val_tn: 911.0000 - val_fn: 109.0000 - val_accuracy: 0.7993 - val_precision: 0.5474 - val_recall: 0.6562 - val_auc: 0.8380 - val_prc: 0.6609
Epoch 148/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5179 - tp: 537.5000 - fp: 540.5000 - tn: 2916.2500 - fn: 305.7500 - accuracy: 0.8045 - precision: 0.4972 - recall: 0.6392 - auc: 0.8256 - prc: 0.5698 - val_loss: 0.4633 - val_tp: 209.0000 - val_fp: 171.0000 - val_tn: 912.0000 - val_fn: 108.0000 - val_accuracy: 0.8007 - val_precision: 0.5500 - val_recall: 0.6593 - val_auc: 0.8389 - val_prc: 0.6610
Epoch 149/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5293 - tp: 514.2500 - fp: 547.5000 - tn: 2905.5000 - fn: 332.7500 - accuracy: 0.7952 - precision: 0.4824 - recall: 0.6019 - auc: 0.8160 - prc: 0.5562 - val_loss: 0.4627 - val_tp: 208.0000 - val_fp: 173.0000 - val_tn: 910.0000 - val_fn: 109.0000 - val_accuracy: 0.7986 - val_precision: 0.5459 - val_recall: 0.6562 - val_auc: 0.8388 - val_prc: 0.6599
Epoch 150/200
3/3 [==============================] - 0s 16ms/step - loss: 0.5479 - tp: 516.7500 - fp: 549.5000 - tn: 2882.0000 - fn: 351.7500 - accuracy: 0.7897 - precision: 0.4891 - recall: 0.5931 - auc: 0.8104 - prc: 0.5592 - val_loss: 0.4646 - val_tp: 209.0000 - val_fp: 178.0000 - val_tn: 905.0000 - val_fn: 108.0000 - val_accuracy: 0.7957 - val_precision: 0.5401 - val_recall: 0.6593 - val_auc: 0.8389 - val_prc: 0.6588
Epoch 151/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5345 - tp: 542.5000 - fp: 558.5000 - tn: 2889.5000 - fn: 309.5000 - accuracy: 0.7989 - precision: 0.4933 - recall: 0.6366 - auc: 0.8135 - prc: 0.5483 - val_loss: 0.4650 - val_tp: 209.0000 - val_fp: 178.0000 - val_tn: 905.0000 - val_fn: 108.0000 - val_accuracy: 0.7957 - val_precision: 0.5401 - val_recall: 0.6593 - val_auc: 0.8390 - val_prc: 0.6585
Epoch 152/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5330 - tp: 513.5000 - fp: 559.7500 - tn: 2894.0000 - fn: 332.7500 - accuracy: 0.7924 - precision: 0.4768 - recall: 0.6060 - auc: 0.8120 - prc: 0.5565 - val_loss: 0.4650 - val_tp: 208.0000 - val_fp: 178.0000 - val_tn: 905.0000 - val_fn: 109.0000 - val_accuracy: 0.7950 - val_precision: 0.5389 - val_recall: 0.6562 - val_auc: 0.8392 - val_prc: 0.6579
Epoch 153/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5397 - tp: 549.7500 - fp: 581.7500 - tn: 2858.7500 - fn: 309.7500 - accuracy: 0.7920 - precision: 0.4867 - recall: 0.6386 - auc: 0.8161 - prc: 0.5409 - val_loss: 0.4650 - val_tp: 208.0000 - val_fp: 178.0000 - val_tn: 905.0000 - val_fn: 109.0000 - val_accuracy: 0.7950 - val_precision: 0.5389 - val_recall: 0.6562 - val_auc: 0.8397 - val_prc: 0.6598
Epoch 154/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5243 - tp: 546.0000 - fp: 558.7500 - tn: 2891.7500 - fn: 303.5000 - accuracy: 0.7989 - precision: 0.4937 - recall: 0.6456 - auc: 0.8204 - prc: 0.5715 - val_loss: 0.4634 - val_tp: 208.0000 - val_fp: 175.0000 - val_tn: 908.0000 - val_fn: 109.0000 - val_accuracy: 0.7971 - val_precision: 0.5431 - val_recall: 0.6562 - val_auc: 0.8401 - val_prc: 0.6606
Epoch 155/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5270 - tp: 542.2500 - fp: 556.7500 - tn: 2888.0000 - fn: 313.0000 - accuracy: 0.7997 - precision: 0.4970 - recall: 0.6347 - auc: 0.8208 - prc: 0.5628 - val_loss: 0.4631 - val_tp: 208.0000 - val_fp: 175.0000 - val_tn: 908.0000 - val_fn: 109.0000 - val_accuracy: 0.7971 - val_precision: 0.5431 - val_recall: 0.6562 - val_auc: 0.8404 - val_prc: 0.6611
Epoch 156/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5316 - tp: 534.2500 - fp: 544.5000 - tn: 2900.5000 - fn: 320.7500 - accuracy: 0.7998 - precision: 0.4966 - recall: 0.6253 - auc: 0.8172 - prc: 0.5575 - val_loss: 0.4621 - val_tp: 207.0000 - val_fp: 172.0000 - val_tn: 911.0000 - val_fn: 110.0000 - val_accuracy: 0.7986 - val_precision: 0.5462 - val_recall: 0.6530 - val_auc: 0.8407 - val_prc: 0.6618
Epoch 157/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5292 - tp: 524.0000 - fp: 533.2500 - tn: 2913.7500 - fn: 329.0000 - accuracy: 0.7977 - precision: 0.4928 - recall: 0.6119 - auc: 0.8178 - prc: 0.5681 - val_loss: 0.4604 - val_tp: 207.0000 - val_fp: 170.0000 - val_tn: 913.0000 - val_fn: 110.0000 - val_accuracy: 0.8000 - val_precision: 0.5491 - val_recall: 0.6530 - val_auc: 0.8411 - val_prc: 0.6643
Epoch 158/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5393 - tp: 529.5000 - fp: 534.7500 - tn: 2906.7500 - fn: 329.0000 - accuracy: 0.7982 - precision: 0.4979 - recall: 0.6170 - auc: 0.8125 - prc: 0.5600 - val_loss: 0.4614 - val_tp: 207.0000 - val_fp: 170.0000 - val_tn: 913.0000 - val_fn: 110.0000 - val_accuracy: 0.8000 - val_precision: 0.5491 - val_recall: 0.6530 - val_auc: 0.8415 - val_prc: 0.6650
Epoch 159/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5322 - tp: 530.2500 - fp: 555.5000 - tn: 2890.7500 - fn: 323.5000 - accuracy: 0.7946 - precision: 0.4870 - recall: 0.6228 - auc: 0.8167 - prc: 0.5530 - val_loss: 0.4626 - val_tp: 207.0000 - val_fp: 170.0000 - val_tn: 913.0000 - val_fn: 110.0000 - val_accuracy: 0.8000 - val_precision: 0.5491 - val_recall: 0.6530 - val_auc: 0.8418 - val_prc: 0.6645
Epoch 160/200
3/3 [==============================] - 0s 21ms/step - loss: 0.5357 - tp: 536.5000 - fp: 579.0000 - tn: 2876.2500 - fn: 308.2500 - accuracy: 0.7913 - precision: 0.4745 - recall: 0.6301 - auc: 0.8091 - prc: 0.5412 - val_loss: 0.4632 - val_tp: 208.0000 - val_fp: 172.0000 - val_tn: 911.0000 - val_fn: 109.0000 - val_accuracy: 0.7993 - val_precision: 0.5474 - val_recall: 0.6562 - val_auc: 0.8418 - val_prc: 0.6649
Epoch 161/200
3/3 [==============================] - 0s 32ms/step - loss: 0.5202 - tp: 534.2500 - fp: 580.7500 - tn: 2873.0000 - fn: 312.0000 - accuracy: 0.7926 - precision: 0.4795 - recall: 0.6296 - auc: 0.8241 - prc: 0.5655 - val_loss: 0.4623 - val_tp: 209.0000 - val_fp: 172.0000 - val_tn: 911.0000 - val_fn: 108.0000 - val_accuracy: 0.8000 - val_precision: 0.5486 - val_recall: 0.6593 - val_auc: 0.8422 - val_prc: 0.6664
Epoch 162/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5302 - tp: 529.2500 - fp: 550.0000 - tn: 2895.2500 - fn: 325.5000 - accuracy: 0.7960 - precision: 0.4913 - recall: 0.6194 - auc: 0.8185 - prc: 0.5610 - val_loss: 0.4618 - val_tp: 209.0000 - val_fp: 177.0000 - val_tn: 906.0000 - val_fn: 108.0000 - val_accuracy: 0.7964 - val_precision: 0.5415 - val_recall: 0.6593 - val_auc: 0.8424 - val_prc: 0.6676
Epoch 163/200
3/3 [==============================] - 0s 21ms/step - loss: 0.5193 - tp: 539.2500 - fp: 544.5000 - tn: 2902.5000 - fn: 313.7500 - accuracy: 0.8003 - precision: 0.4990 - recall: 0.6304 - auc: 0.8264 - prc: 0.5798 - val_loss: 0.4620 - val_tp: 210.0000 - val_fp: 176.0000 - val_tn: 907.0000 - val_fn: 107.0000 - val_accuracy: 0.7979 - val_precision: 0.5440 - val_recall: 0.6625 - val_auc: 0.8419 - val_prc: 0.6671
Epoch 164/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5331 - tp: 537.2500 - fp: 563.0000 - tn: 2876.7500 - fn: 323.0000 - accuracy: 0.7916 - precision: 0.4869 - recall: 0.6211 - auc: 0.8182 - prc: 0.5651 - val_loss: 0.4622 - val_tp: 210.0000 - val_fp: 178.0000 - val_tn: 905.0000 - val_fn: 107.0000 - val_accuracy: 0.7964 - val_precision: 0.5412 - val_recall: 0.6625 - val_auc: 0.8421 - val_prc: 0.6667
Epoch 165/200
3/3 [==============================] - 0s 21ms/step - loss: 0.5226 - tp: 544.5000 - fp: 554.5000 - tn: 2890.5000 - fn: 310.5000 - accuracy: 0.7995 - precision: 0.4985 - recall: 0.6451 - auc: 0.8261 - prc: 0.5704 - val_loss: 0.4632 - val_tp: 211.0000 - val_fp: 181.0000 - val_tn: 902.0000 - val_fn: 106.0000 - val_accuracy: 0.7950 - val_precision: 0.5383 - val_recall: 0.6656 - val_auc: 0.8416 - val_prc: 0.6660
Epoch 166/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5262 - tp: 534.0000 - fp: 567.0000 - tn: 2885.5000 - fn: 313.5000 - accuracy: 0.7948 - precision: 0.4834 - recall: 0.6254 - auc: 0.8180 - prc: 0.5636 - val_loss: 0.4656 - val_tp: 213.0000 - val_fp: 190.0000 - val_tn: 893.0000 - val_fn: 104.0000 - val_accuracy: 0.7900 - val_precision: 0.5285 - val_recall: 0.6719 - val_auc: 0.8412 - val_prc: 0.6656
Epoch 167/200
3/3 [==============================] - 0s 21ms/step - loss: 0.5242 - tp: 557.5000 - fp: 584.2500 - tn: 2856.0000 - fn: 302.2500 - accuracy: 0.7933 - precision: 0.4895 - recall: 0.6467 - auc: 0.8228 - prc: 0.5720 - val_loss: 0.4671 - val_tp: 216.0000 - val_fp: 190.0000 - val_tn: 893.0000 - val_fn: 101.0000 - val_accuracy: 0.7921 - val_precision: 0.5320 - val_recall: 0.6814 - val_auc: 0.8411 - val_prc: 0.6653
Epoch 168/200
3/3 [==============================] - 0s 21ms/step - loss: 0.5239 - tp: 554.5000 - fp: 573.0000 - tn: 2873.5000 - fn: 299.0000 - accuracy: 0.7993 - precision: 0.4974 - recall: 0.6547 - auc: 0.8273 - prc: 0.5657 - val_loss: 0.4654 - val_tp: 214.0000 - val_fp: 187.0000 - val_tn: 896.0000 - val_fn: 103.0000 - val_accuracy: 0.7929 - val_precision: 0.5337 - val_recall: 0.6751 - val_auc: 0.8412 - val_prc: 0.6660
Epoch 169/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5264 - tp: 529.2500 - fp: 562.2500 - tn: 2887.7500 - fn: 320.7500 - accuracy: 0.7955 - precision: 0.4867 - recall: 0.6217 - auc: 0.8205 - prc: 0.5602 - val_loss: 0.4623 - val_tp: 212.0000 - val_fp: 184.0000 - val_tn: 899.0000 - val_fn: 105.0000 - val_accuracy: 0.7936 - val_precision: 0.5354 - val_recall: 0.6688 - val_auc: 0.8417 - val_prc: 0.6671
Epoch 170/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5182 - tp: 551.2500 - fp: 587.2500 - tn: 2865.2500 - fn: 296.2500 - accuracy: 0.7950 - precision: 0.4841 - recall: 0.6526 - auc: 0.8259 - prc: 0.5740 - val_loss: 0.4578 - val_tp: 208.0000 - val_fp: 178.0000 - val_tn: 905.0000 - val_fn: 109.0000 - val_accuracy: 0.7950 - val_precision: 0.5389 - val_recall: 0.6562 - val_auc: 0.8421 - val_prc: 0.6679
Epoch 171/200
3/3 [==============================] - 0s 20ms/step - loss: 0.5200 - tp: 541.0000 - fp: 530.2500 - tn: 2917.5000 - fn: 311.2500 - accuracy: 0.8041 - precision: 0.5037 - recall: 0.6367 - auc: 0.8256 - prc: 0.5745 - val_loss: 0.4548 - val_tp: 207.0000 - val_fp: 175.0000 - val_tn: 908.0000 - val_fn: 110.0000 - val_accuracy: 0.7964 - val_precision: 0.5419 - val_recall: 0.6530 - val_auc: 0.8423 - val_prc: 0.6681
Epoch 172/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5208 - tp: 544.5000 - fp: 541.0000 - tn: 2907.0000 - fn: 307.5000 - accuracy: 0.8023 - precision: 0.5029 - recall: 0.6374 - auc: 0.8239 - prc: 0.5842 - val_loss: 0.4552 - val_tp: 208.0000 - val_fp: 172.0000 - val_tn: 911.0000 - val_fn: 109.0000 - val_accuracy: 0.7993 - val_precision: 0.5474 - val_recall: 0.6562 - val_auc: 0.8428 - val_prc: 0.6696
Epoch 173/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5211 - tp: 536.2500 - fp: 536.2500 - tn: 2918.7500 - fn: 308.7500 - accuracy: 0.8028 - precision: 0.4959 - recall: 0.6340 - auc: 0.8218 - prc: 0.5597 - val_loss: 0.4570 - val_tp: 208.0000 - val_fp: 176.0000 - val_tn: 907.0000 - val_fn: 109.0000 - val_accuracy: 0.7964 - val_precision: 0.5417 - val_recall: 0.6562 - val_auc: 0.8430 - val_prc: 0.6701
Epoch 174/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5332 - tp: 527.7500 - fp: 549.0000 - tn: 2892.2500 - fn: 331.0000 - accuracy: 0.7933 - precision: 0.4903 - recall: 0.6112 - auc: 0.8206 - prc: 0.5612 - val_loss: 0.4580 - val_tp: 209.0000 - val_fp: 178.0000 - val_tn: 905.0000 - val_fn: 108.0000 - val_accuracy: 0.7957 - val_precision: 0.5401 - val_recall: 0.6593 - val_auc: 0.8431 - val_prc: 0.6709
Epoch 175/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5374 - tp: 541.0000 - fp: 560.5000 - tn: 2882.5000 - fn: 316.0000 - accuracy: 0.7943 - precision: 0.4897 - recall: 0.6292 - auc: 0.8152 - prc: 0.5515 - val_loss: 0.4578 - val_tp: 209.0000 - val_fp: 175.0000 - val_tn: 908.0000 - val_fn: 108.0000 - val_accuracy: 0.7979 - val_precision: 0.5443 - val_recall: 0.6593 - val_auc: 0.8433 - val_prc: 0.6725
Epoch 176/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5168 - tp: 549.2500 - fp: 578.7500 - tn: 2870.2500 - fn: 301.7500 - accuracy: 0.7950 - precision: 0.4857 - recall: 0.6464 - auc: 0.8250 - prc: 0.5766 - val_loss: 0.4569 - val_tp: 208.0000 - val_fp: 172.0000 - val_tn: 911.0000 - val_fn: 109.0000 - val_accuracy: 0.7993 - val_precision: 0.5474 - val_recall: 0.6562 - val_auc: 0.8432 - val_prc: 0.6731
Epoch 177/200
3/3 [==============================] - 0s 20ms/step - loss: 0.5184 - tp: 519.0000 - fp: 558.5000 - tn: 2904.0000 - fn: 318.5000 - accuracy: 0.7959 - precision: 0.4769 - recall: 0.6193 - auc: 0.8209 - prc: 0.5579 - val_loss: 0.4558 - val_tp: 207.0000 - val_fp: 167.0000 - val_tn: 916.0000 - val_fn: 110.0000 - val_accuracy: 0.8021 - val_precision: 0.5535 - val_recall: 0.6530 - val_auc: 0.8436 - val_prc: 0.6736
Epoch 178/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5233 - tp: 552.7500 - fp: 549.0000 - tn: 2893.5000 - fn: 304.7500 - accuracy: 0.8024 - precision: 0.5045 - recall: 0.6475 - auc: 0.8254 - prc: 0.5775 - val_loss: 0.4570 - val_tp: 208.0000 - val_fp: 173.0000 - val_tn: 910.0000 - val_fn: 109.0000 - val_accuracy: 0.7986 - val_precision: 0.5459 - val_recall: 0.6562 - val_auc: 0.8435 - val_prc: 0.6739
Epoch 179/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5150 - tp: 546.0000 - fp: 543.5000 - tn: 2908.0000 - fn: 302.5000 - accuracy: 0.8043 - precision: 0.5020 - recall: 0.6452 - auc: 0.8282 - prc: 0.5758 - val_loss: 0.4577 - val_tp: 208.0000 - val_fp: 174.0000 - val_tn: 909.0000 - val_fn: 109.0000 - val_accuracy: 0.7979 - val_precision: 0.5445 - val_recall: 0.6562 - val_auc: 0.8435 - val_prc: 0.6740
Epoch 180/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5260 - tp: 526.7500 - fp: 553.5000 - tn: 2895.0000 - fn: 324.7500 - accuracy: 0.7962 - precision: 0.4883 - recall: 0.6128 - auc: 0.8200 - prc: 0.5700 - val_loss: 0.4595 - val_tp: 209.0000 - val_fp: 178.0000 - val_tn: 905.0000 - val_fn: 108.0000 - val_accuracy: 0.7957 - val_precision: 0.5401 - val_recall: 0.6593 - val_auc: 0.8433 - val_prc: 0.6738
Epoch 181/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5215 - tp: 527.5000 - fp: 562.2500 - tn: 2892.0000 - fn: 318.2500 - accuracy: 0.7951 - precision: 0.4833 - recall: 0.6202 - auc: 0.8235 - prc: 0.5647 - val_loss: 0.4605 - val_tp: 210.0000 - val_fp: 180.0000 - val_tn: 903.0000 - val_fn: 107.0000 - val_accuracy: 0.7950 - val_precision: 0.5385 - val_recall: 0.6625 - val_auc: 0.8432 - val_prc: 0.6728
Epoch 182/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5288 - tp: 549.5000 - fp: 574.0000 - tn: 2869.2500 - fn: 307.2500 - accuracy: 0.7940 - precision: 0.4890 - recall: 0.6442 - auc: 0.8204 - prc: 0.5751 - val_loss: 0.4615 - val_tp: 210.0000 - val_fp: 181.0000 - val_tn: 902.0000 - val_fn: 107.0000 - val_accuracy: 0.7943 - val_precision: 0.5371 - val_recall: 0.6625 - val_auc: 0.8431 - val_prc: 0.6726
Epoch 183/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5218 - tp: 541.7500 - fp: 574.0000 - tn: 2871.0000 - fn: 313.2500 - accuracy: 0.7941 - precision: 0.4874 - recall: 0.6322 - auc: 0.8231 - prc: 0.5846 - val_loss: 0.4620 - val_tp: 209.0000 - val_fp: 181.0000 - val_tn: 902.0000 - val_fn: 108.0000 - val_accuracy: 0.7936 - val_precision: 0.5359 - val_recall: 0.6593 - val_auc: 0.8430 - val_prc: 0.6720
Epoch 184/200
3/3 [==============================] - 0s 18ms/step - loss: 0.4996 - tp: 553.0000 - fp: 556.2500 - tn: 2893.7500 - fn: 297.0000 - accuracy: 0.8037 - precision: 0.5027 - recall: 0.6503 - auc: 0.8408 - prc: 0.6065 - val_loss: 0.4619 - val_tp: 209.0000 - val_fp: 184.0000 - val_tn: 899.0000 - val_fn: 108.0000 - val_accuracy: 0.7914 - val_precision: 0.5318 - val_recall: 0.6593 - val_auc: 0.8429 - val_prc: 0.6715
Epoch 185/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5033 - tp: 566.0000 - fp: 558.5000 - tn: 2890.0000 - fn: 285.5000 - accuracy: 0.8032 - precision: 0.5028 - recall: 0.6626 - auc: 0.8395 - prc: 0.5925 - val_loss: 0.4600 - val_tp: 208.0000 - val_fp: 182.0000 - val_tn: 901.0000 - val_fn: 109.0000 - val_accuracy: 0.7921 - val_precision: 0.5333 - val_recall: 0.6562 - val_auc: 0.8425 - val_prc: 0.6711
Epoch 186/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5277 - tp: 532.0000 - fp: 573.2500 - tn: 2873.0000 - fn: 321.7500 - accuracy: 0.7938 - precision: 0.4860 - recall: 0.6233 - auc: 0.8164 - prc: 0.5676 - val_loss: 0.4587 - val_tp: 208.0000 - val_fp: 179.0000 - val_tn: 904.0000 - val_fn: 109.0000 - val_accuracy: 0.7943 - val_precision: 0.5375 - val_recall: 0.6562 - val_auc: 0.8425 - val_prc: 0.6703
Epoch 187/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5197 - tp: 551.5000 - fp: 566.0000 - tn: 2889.2500 - fn: 293.2500 - accuracy: 0.8000 - precision: 0.4914 - recall: 0.6509 - auc: 0.8188 - prc: 0.5695 - val_loss: 0.4566 - val_tp: 207.0000 - val_fp: 173.0000 - val_tn: 910.0000 - val_fn: 110.0000 - val_accuracy: 0.7979 - val_precision: 0.5447 - val_recall: 0.6530 - val_auc: 0.8429 - val_prc: 0.6712
Epoch 188/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5260 - tp: 536.2500 - fp: 543.2500 - tn: 2896.2500 - fn: 324.2500 - accuracy: 0.8010 - precision: 0.5046 - recall: 0.6245 - auc: 0.8234 - prc: 0.5766 - val_loss: 0.4567 - val_tp: 207.0000 - val_fp: 175.0000 - val_tn: 908.0000 - val_fn: 110.0000 - val_accuracy: 0.7964 - val_precision: 0.5419 - val_recall: 0.6530 - val_auc: 0.8428 - val_prc: 0.6707
Epoch 189/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5130 - tp: 558.0000 - fp: 550.5000 - tn: 2898.2500 - fn: 293.2500 - accuracy: 0.8046 - precision: 0.5030 - recall: 0.6587 - auc: 0.8310 - prc: 0.5730 - val_loss: 0.4566 - val_tp: 208.0000 - val_fp: 171.0000 - val_tn: 912.0000 - val_fn: 109.0000 - val_accuracy: 0.8000 - val_precision: 0.5488 - val_recall: 0.6562 - val_auc: 0.8433 - val_prc: 0.6722
Epoch 190/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5178 - tp: 556.0000 - fp: 561.7500 - tn: 2885.5000 - fn: 296.7500 - accuracy: 0.8001 - precision: 0.4963 - recall: 0.6521 - auc: 0.8280 - prc: 0.5747 - val_loss: 0.4561 - val_tp: 207.0000 - val_fp: 170.0000 - val_tn: 913.0000 - val_fn: 110.0000 - val_accuracy: 0.8000 - val_precision: 0.5491 - val_recall: 0.6530 - val_auc: 0.8433 - val_prc: 0.6728
Epoch 191/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5162 - tp: 537.7500 - fp: 534.7500 - tn: 2915.7500 - fn: 311.7500 - accuracy: 0.8029 - precision: 0.5004 - recall: 0.6321 - auc: 0.8290 - prc: 0.5688 - val_loss: 0.4555 - val_tp: 208.0000 - val_fp: 169.0000 - val_tn: 914.0000 - val_fn: 109.0000 - val_accuracy: 0.8014 - val_precision: 0.5517 - val_recall: 0.6562 - val_auc: 0.8435 - val_prc: 0.6736
Epoch 192/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5238 - tp: 522.5000 - fp: 554.5000 - tn: 2892.7500 - fn: 330.2500 - accuracy: 0.7946 - precision: 0.4859 - recall: 0.6081 - auc: 0.8255 - prc: 0.5668 - val_loss: 0.4541 - val_tp: 208.0000 - val_fp: 170.0000 - val_tn: 913.0000 - val_fn: 109.0000 - val_accuracy: 0.8007 - val_precision: 0.5503 - val_recall: 0.6562 - val_auc: 0.8440 - val_prc: 0.6739
Epoch 193/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5220 - tp: 540.2500 - fp: 551.2500 - tn: 2897.7500 - fn: 310.7500 - accuracy: 0.7996 - precision: 0.4951 - recall: 0.6334 - auc: 0.8253 - prc: 0.5737 - val_loss: 0.4538 - val_tp: 209.0000 - val_fp: 169.0000 - val_tn: 914.0000 - val_fn: 108.0000 - val_accuracy: 0.8021 - val_precision: 0.5529 - val_recall: 0.6593 - val_auc: 0.8443 - val_prc: 0.6745
Epoch 194/200
3/3 [==============================] - 0s 17ms/step - loss: 0.5111 - tp: 533.5000 - fp: 551.0000 - tn: 2903.5000 - fn: 312.0000 - accuracy: 0.8003 - precision: 0.4906 - recall: 0.6317 - auc: 0.8287 - prc: 0.5813 - val_loss: 0.4543 - val_tp: 210.0000 - val_fp: 171.0000 - val_tn: 912.0000 - val_fn: 107.0000 - val_accuracy: 0.8014 - val_precision: 0.5512 - val_recall: 0.6625 - val_auc: 0.8445 - val_prc: 0.6753
Epoch 195/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5123 - tp: 541.2500 - fp: 547.5000 - tn: 2910.7500 - fn: 300.5000 - accuracy: 0.8018 - precision: 0.4936 - recall: 0.6399 - auc: 0.8284 - prc: 0.5784 - val_loss: 0.4559 - val_tp: 210.0000 - val_fp: 176.0000 - val_tn: 907.0000 - val_fn: 107.0000 - val_accuracy: 0.7979 - val_precision: 0.5440 - val_recall: 0.6625 - val_auc: 0.8448 - val_prc: 0.6750
Epoch 196/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5136 - tp: 557.0000 - fp: 547.2500 - tn: 2899.7500 - fn: 296.0000 - accuracy: 0.8045 - precision: 0.5057 - recall: 0.6518 - auc: 0.8293 - prc: 0.5826 - val_loss: 0.4586 - val_tp: 211.0000 - val_fp: 177.0000 - val_tn: 906.0000 - val_fn: 106.0000 - val_accuracy: 0.7979 - val_precision: 0.5438 - val_recall: 0.6656 - val_auc: 0.8450 - val_prc: 0.6752
Epoch 197/200
3/3 [==============================] - 0s 20ms/step - loss: 0.5069 - tp: 554.5000 - fp: 585.2500 - tn: 2856.2500 - fn: 304.0000 - accuracy: 0.7926 - precision: 0.4863 - recall: 0.6477 - auc: 0.8361 - prc: 0.5958 - val_loss: 0.4589 - val_tp: 212.0000 - val_fp: 178.0000 - val_tn: 905.0000 - val_fn: 105.0000 - val_accuracy: 0.7979 - val_precision: 0.5436 - val_recall: 0.6688 - val_auc: 0.8451 - val_prc: 0.6756
Epoch 198/200
3/3 [==============================] - 0s 19ms/step - loss: 0.5108 - tp: 555.5000 - fp: 586.5000 - tn: 2864.2500 - fn: 293.7500 - accuracy: 0.7951 - precision: 0.4844 - recall: 0.6517 - auc: 0.8310 - prc: 0.5801 - val_loss: 0.4572 - val_tp: 212.0000 - val_fp: 176.0000 - val_tn: 907.0000 - val_fn: 105.0000 - val_accuracy: 0.7993 - val_precision: 0.5464 - val_recall: 0.6688 - val_auc: 0.8457 - val_prc: 0.6769
Epoch 199/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5169 - tp: 546.5000 - fp: 580.2500 - tn: 2868.7500 - fn: 304.5000 - accuracy: 0.7949 - precision: 0.4872 - recall: 0.6449 - auc: 0.8293 - prc: 0.5751 - val_loss: 0.4552 - val_tp: 211.0000 - val_fp: 174.0000 - val_tn: 909.0000 - val_fn: 106.0000 - val_accuracy: 0.8000 - val_precision: 0.5481 - val_recall: 0.6656 - val_auc: 0.8457 - val_prc: 0.6770
Epoch 200/200
3/3 [==============================] - 0s 18ms/step - loss: 0.5162 - tp: 553.5000 - fp: 567.0000 - tn: 2876.2500 - fn: 303.2500 - accuracy: 0.7968 - precision: 0.4952 - recall: 0.6453 - auc: 0.8263 - prc: 0.5945 - val_loss: 0.4539 - val_tp: 210.0000 - val_fp: 172.0000 - val_tn: 911.0000 - val_fn: 107.0000 - val_accuracy: 0.8007 - val_precision: 0.5497 - val_recall: 0.6625 - val_auc: 0.8460 - val_prc: 0.6776
CPU times: user 20.4 s, sys: 7.09 s, total: 27.5 s
Wall time: 12.9 s


model4.summary()

Model: "sequential_4"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense_9 (Dense)              (None, 64)                768       
_________________________________________________________________
dropout_4 (Dropout)          (None, 64)                0         
_________________________________________________________________
dense_10 (Dense)             (None, 16)                1040      
_________________________________________________________________
dropout_5 (Dropout)          (None, 16)                0         
_________________________________________________________________
dense_11 (Dense)             (None, 1)                 17        
=================================================================
Total params: 1,825
Trainable params: 1,825
Non-trainable params: 0
_________________________________________________________________


history_df = pd.DataFrame(history4.history)
history_df['epoch']=history4.epoch
display(history_df)
train_acc = history_df.loc[199,'accuracy']
train_recall = history_df.loc[199,'recall']
train_loss = history_df.loc[199,'loss']


results_df = results_df.loc[:,['model1','model2','model2-tanh']]

results4=model4.evaluate(X_test, y_test.values)

temp_df = pd.DataFrame(results4, index=model3.metrics_names, columns=['model4'])

results_df = pd.merge(results_df, temp_df, left_index=True, right_index=True)

results_df

94/94 [==============================] - 0s 1ms/step - loss: 0.4476 - tp: 431.0000 - fp: 378.0000 - tn: 2011.0000 - fn: 180.0000 - accuracy: 0.8140 - precision: 0.5328 - recall: 0.7054 - auc: 0.8525 - prc: 0.6731


plt.figure(figsize=(10,10))
plot_metrics(history4)


y_predict = (model4.predict(X_test) > THRESHOLD).astype('int32')
make_confusion_matrix(model4,y_test, y_predict, cmap='jet')


print(f'Model test loss is: {results_df.loc["loss","model4"]:0.4f}, train loss is {train_loss:0.4f}')
print(f'Model test accuracy is: {results_df.loc["accuracy","model4"]:0.4f}, train accuracy is {train_acc:0.4f}')
print(f'Model test recall is: {results_df.loc["recall","model4"]:0.4f}, train recall is {train_recall:0.4f}')

Model test loss is: 0.5097, train loss is 0.5437
Model test accuracy is: 0.8077, train accuracy is 0.7770
Model test recall is: 0.6710, train recall is 0.6510


import xgboost as xgb
from xgboost import XGBClassifier

from sklearn.model_selection import RandomizedSearchCV
from sklearn.metrics import plot_confusion_matrix, accuracy_score, recall_score, make_scorer

#xgb.config_context()


params= {
        'n_estimators': np.arange(10,150,10),
        'scale_pos_weight': [(neg/pos)], 
        'learning_rate': [0.05,0.1,0.2,0.3], 
        'gamma': np.arange(0,150,10),
        'subsample': [0.5,0.6,0.7,0.8,0.9,1],
        'colsample_bytree': [0.1,0.2,0.3,0.5,0.7,1],
        'max_depth': [3,5,6,8,10,12,15],
        'tree_method': ['hist'], 
        'min_child_weight': [0,3,5,7,8,9,10],
        'colsample_bylevel': [0.5,0.7,1]
    }


%%time
modelx = XGBClassifier()
scorer = metrics.make_scorer(metrics.recall_score)
cvobj = RandomizedSearchCV(estimator=modelx, param_distributions=params, n_iter=50, \
                            scoring=scorer, cv=5, random_state=random_state)


cvobj.fit(X_train, y_train)

CPU times: user 13min 35s, sys: 1min 7s, total: 14min 43s
Wall time: 1min 5s

RandomizedSearchCV(cv=5,
                   estimator=XGBClassifier(base_score=None, booster=None,
                                           colsample_bylevel=None,
                                           colsample_bynode=None,
                                           colsample_bytree=None, gamma=None,
                                           gpu_id=None, importance_type='gain',
                                           interaction_constraints=None,
                                           learning_rate=None,
                                           max_delta_step=None, max_depth=None,
                                           min_child_weight=None, missing=nan,
                                           monotone_constraints=None,
                                           n_estimators=100,...
                                        'gamma': array([  0,  10,  20,  30,  40,  50,  60,  70,  80,  90, 100, 110, 120,
       130, 140]),
                                        'learning_rate': [0.05, 0.1, 0.2, 0.3],
                                        'max_depth': [3, 5, 6, 8, 10, 12, 15],
                                        'min_child_weight': [0, 3, 5, 7, 8, 9,
                                                             10],
                                        'n_estimators': array([ 10,  20,  30,  40,  50,  60,  70,  80,  90, 100, 110, 120, 130,
       140]),
                                        'scale_pos_weight': [3.9091801669121256],
                                        'subsample': [0.5, 0.6, 0.7, 0.8, 0.9,
                                                      1],
                                        'tree_method': ['hist']},
                   random_state=314159, scoring=make_scorer(recall_score))


cvobj.best_estimator_

XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, gamma=40, gpu_id=-1,
              importance_type='gain', interaction_constraints='',
              learning_rate=0.2, max_delta_step=0, max_depth=6,
              min_child_weight=3, missing=nan, monotone_constraints='()',
              n_estimators=60, n_jobs=0, num_parallel_tree=1, random_state=0,
              reg_alpha=0, reg_lambda=1, scale_pos_weight=3.9091801669121256,
              subsample=0.6, tree_method='hist', validate_parameters=1,
              verbosity=None)


yypred=cvobj.predict(X_test)


make_confusion_matrix(cvobj, y_test, cmap='Greens')

print(f'accuracy: {accuracy_score(y_test, yypred)}, recall: {recall_score(y_test, yypred)}')

accuracy: 0.792, recall: 0.7430441898527005

	RowNumber	CustomerId	Surname	CreditScore	Geography	Gender	Age	Tenure	Balance	NumOfProducts	HasCrCard	IsActiveMember	EstimatedSalary	Exited
0	1	15634602	Hargrave	619	France	Female	42	2	0.00	1	1	1	101348.88	1
1	2	15647311	Hill	608	Spain	Female	41	1	83807.86	1	0	1	112542.58	0
2	3	15619304	Onio	502	France	Female	42	8	159660.80	3	1	0	113931.57	1
3	4	15701354	Boni	699	France	Female	39	1	0.00	2	0	0	93826.63	0
4	5	15737888	Mitchell	850	Spain	Female	43	2	125510.82	1	1	1	79084.10	0

	CreditScore	Age	Tenure	Balance	NumOfProducts	HasCrCard	IsActiveMember	EstimatedSalary
Exited
0	651.853196	37.408389	5.033279	72745.296779	1.544267	0.707146	0.554565	99738.391772
1	645.351497	44.837997	4.932744	91108.539337	1.475209	0.699067	0.360825	101465.677531

Gender	Female	Male
Exited
0	0.749285	0.835441
1	0.250715	0.164559

Geography	France	Germany	Spain
Exited
0	0.838452	0.675568	0.833266
1	0.161548	0.324432	0.166734

HasCrCard	0	1
Exited
0	0.791851	0.798157
1	0.208149	0.201843

Pre Work¶

Load Libraries and Define Custom Functions¶

1. Load and Inspect Data¶

2.A EDA - Univariate Analysis¶

2.A (i) Credit Score¶

2.A (ii) Age¶

2.A (iii) Estimated Salary¶

2.A (iv) Balance¶

2.A (v) Tenure¶

2.A (vi) NumOfProducts¶

2.A (vii) HasCrCard¶

2.A (viii) IsActiveMember¶

2.A (ix) Exited (Target Variable)¶

2.A (x) Geography¶

2.A (xi) Gender¶

2.B Bivariate Analysis¶

Examining bivariate relationships - vs. Exited¶

Bivariate vs. Balance¶

3. Data Preprocessing¶

4. Modelling¶

Function and Constants needed for section¶

4.A Base model - only one hidden layer and few nodes¶

4.B Refining the ANN Model - using class weights¶

4.C Using Tanh as activation for the hidden layers¶

4.D Trying more complex model -¶

Final Conclusions and Business Recommendations¶

Appendix: Using XGBoost to check ANN performance¶

	count	mean	std	min	25%	50%	75%	max
RowNumber	10000.0	5.000500e+03	2886.895680	1.00	2500.75	5.000500e+03	7.500250e+03	10000.00
CustomerId	10000.0	1.569094e+07	71936.186123	15565701.00	15628528.25	1.569074e+07	1.575323e+07	15815690.00
CreditScore	10000.0	6.505288e+02	96.653299	350.00	584.00	6.520000e+02	7.180000e+02	850.00
Age	10000.0	3.892180e+01	10.487806	18.00	32.00	3.700000e+01	4.400000e+01	92.00
Tenure	10000.0	5.012800e+00	2.892174	0.00	3.00	5.000000e+00	7.000000e+00	10.00
Balance	10000.0	7.648589e+04	62397.405202	0.00	0.00	9.719854e+04	1.276442e+05	250898.09
NumOfProducts	10000.0	1.530200e+00	0.581654	1.00	1.00	1.000000e+00	2.000000e+00	4.00
HasCrCard	10000.0	7.055000e-01	0.455840	0.00	0.00	1.000000e+00	1.000000e+00	1.00
IsActiveMember	10000.0	5.151000e-01	0.499797	0.00	0.00	1.000000e+00	1.000000e+00	1.00
EstimatedSalary	10000.0	1.000902e+05	57510.492818	11.58	51002.11	1.001939e+05	1.493882e+05	199992.48
Exited	10000.0	2.037000e-01	0.402769	0.00	0.00	0.000000e+00	0.000000e+00	1.00

	count	unique	top	freq
Surname	10000	2932	Smith	32
Geography	10000	3	France	5014
Gender	10000	2	Male	5457

	n_uniques	col_types	isnumeric_column	probably_categorical
CreditScore	460	int64	True	False
Age	70	int64	True	False
Tenure	11	int64	True	True
NumOfProducts	4	int64	True	True
HasCrCard	2	int64	True	True
IsActiveMember	2	int64	True	True
Exited	2	int64	True	True
Balance	6382	float64	True	False
EstimatedSalary	9999	float64	True	False
Geography	3	object	False	True
Gender	2	object	False	True

	CreditScore	Age	Tenure	Balance	NumOfProducts	HasCrCard	IsActiveMember	EstimatedSalary
Exited
0	653	36	5	92072.68	2	1	1	99645.04
1	646	45	5	109349.29	1	1	0	102460.84

NumOfProducts	1	2	3	4
Exited
0	0.722856	0.924183	0.172932	0.0
1	0.277144	0.075817	0.827068	1.0

Tenure	0	1	2	3	4	5	6	7	8	9	10
Exited
0	0.769976	0.775845	0.808206	0.7889	0.794742	0.793478	0.797311	0.827821	0.807805	0.783537	0.793878
1	0.230024	0.224155	0.191794	0.2111	0.205258	0.206522	0.202689	0.172179	0.192195	0.216463	0.206122

	CreditScore	Age	Tenure	Balance	NumOfProducts	HasCrCard	IsActiveMember	EstimatedSalary	Exited
BalanceZero
0	651.138493	39.197713	4.979633	119827.493793	1.386025	0.699201	0.513552	100717.352956	0.240796
1	649.452861	38.434891	5.071330	0.000000	1.784628	0.716616	0.517832	98983.559549	0.138236

	CreditScore	Age	Tenure	Balance	NumOfProducts	HasCrCard	IsActiveMember	EstimatedSalary	Geography_Germany	Geography_Spain	Gender_Male
2441	735	29	10	0.00	2	1	1	95025.27	0	1	1
2786	511	40	9	124401.60	1	1	0	198814.24	1	0	0
2375	815	39	6	0.00	1	1	1	85167.88	0	1	0
3566	746	25	3	104833.79	1	0	0	71911.30	0	1	0
7616	610	27	4	87262.40	2	1	0	182720.07	0	0	0
...	...	...	...	...	...	...	...	...	...	...	...
2513	666	39	10	0.00	2	1	0	102999.33	0	0	1
8474	721	33	4	72535.45	1	1	1	103931.49	0	1	0
4528	714	31	6	152926.60	1	1	1	50899.91	0	1	0
1732	735	49	5	121973.28	1	1	0	148804.36	0	0	1
5914	754	27	7	117578.35	2	0	1	87908.01	1	0	1

	count	mean	std	min	25%	50%	75%	max
CreditScore	7000.0	-0.011733	0.719086	-2.253731	-0.514925	0.000000e+00	0.485075	1.477612
Age	7000.0	0.168060	0.881617	-1.583333	-0.416667	0.000000e+00	0.583333	4.583333
Tenure	7000.0	-0.001743	0.578801	-1.000000	-0.600000	0.000000e+00	0.400000	1.000000
Balance	7000.0	-0.164601	0.490244	-0.761774	-0.761774	-5.722110e-17	0.238226	1.211395
NumOfProducts	7000.0	0.526571	0.579087	0.000000	0.000000	0.000000e+00	1.000000	3.000000
HasCrCard	7000.0	-0.293000	0.455171	-1.000000	-1.000000	0.000000e+00	0.000000	0.000000
IsActiveMember	7000.0	-0.480714	0.499664	-1.000000	-1.000000	0.000000e+00	0.000000	0.000000
EstimatedSalary	7000.0	0.001752	0.589707	-1.028401	-0.494425	7.470153e-17	0.505575	1.024988
Geography_Germany	7000.0	0.251571	0.433947	0.000000	0.000000	0.000000e+00	1.000000	1.000000
Geography_Spain	7000.0	0.251571	0.433947	0.000000	0.000000	0.000000e+00	1.000000	1.000000
Gender_Male	7000.0	-0.455571	0.498058	-1.000000	-1.000000	0.000000e+00	0.000000	0.000000

	count	mean	std	min	25%	50%	75%	max
CreditScore	3000.0	-0.009219	0.726535	-2.253731	-0.507463	-0.007463	0.501866	1.477612
Age	3000.0	0.141694	0.855769	-1.583333	-0.416667	0.000000	0.500000	4.583333
Tenure	3000.0	0.012600	0.577552	-1.000000	-0.400000	0.000000	0.600000	1.000000
Balance	3000.0	-0.150121	0.491760	-0.761774	-0.761774	0.007951	0.250175	1.113007
NumOfProducts	3000.0	0.538667	0.587611	0.000000	0.000000	0.000000	1.000000	3.000000
HasCrCard	3000.0	-0.298000	0.457456	-1.000000	-1.000000	0.000000	0.000000	0.000000
IsActiveMember	3000.0	-0.494667	0.500055	-1.000000	-1.000000	0.000000	0.000000	0.000000
EstimatedSalary	3000.0	-0.006758	0.592448	-1.027595	-0.520785	0.002163	0.504898	1.024338
Geography_Germany	3000.0	0.249333	0.432699	0.000000	0.000000	0.000000	0.000000	1.000000
Geography_Spain	3000.0	0.238667	0.426340	0.000000	0.000000	0.000000	0.000000	1.000000
Gender_Male	3000.0	-0.451333	0.497709	-1.000000	-1.000000	0.000000	0.000000	0.000000

IsActiveMember	0	1
Exited
0	0.731491	0.857309
1	0.268509	0.142691

	loss	tp	fp	tn	fn	accuracy	precision	recall	auc	prc	...	val_tp	val_fp	val_tn	val_fn	val_accuracy	val_precision	val_recall	val_auc	val_prc	epoch
0	0.536275	0.0	0.0	4491.0	1109.0	0.801964	0.000000	0.000000	0.425088	0.196332	...	0.0	0.0	1083.0	317.0	0.773571	0.000000	0.000000	0.502400	0.244597	0
1	0.488402	0.0	0.0	4491.0	1109.0	0.801964	0.000000	0.000000	0.611210	0.295439	...	0.0	0.0	1083.0	317.0	0.773571	0.000000	0.000000	0.652885	0.330409	1
2	0.461690	2.0	2.0	4489.0	1107.0	0.801964	0.500000	0.001803	0.710733	0.366269	...	0.0	0.0	1083.0	317.0	0.773571	0.000000	0.000000	0.711723	0.381195	2
3	0.445066	13.0	9.0	4482.0	1096.0	0.802679	0.590909	0.011722	0.746552	0.397383	...	6.0	9.0	1074.0	311.0	0.771429	0.400000	0.018927	0.732584	0.401068	3
4	0.434225	49.0	36.0	4455.0	1060.0	0.804286	0.576471	0.044184	0.760256	0.422323	...	15.0	20.0	1063.0	302.0	0.770000	0.428571	0.047319	0.740785	0.412946	4
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
95	0.322830	521.0	149.0	4342.0	588.0	0.868393	0.777612	0.469793	0.873079	0.708214	...	145.0	52.0	1031.0	172.0	0.840000	0.736041	0.457413	0.845870	0.678736	95
96	0.323012	519.0	155.0	4336.0	590.0	0.866964	0.770030	0.467989	0.872875	0.708064	...	132.0	42.0	1041.0	185.0	0.837857	0.758621	0.416404	0.845580	0.677532	96
97	0.322813	530.0	163.0	4328.0	579.0	0.867500	0.764791	0.477908	0.872822	0.708369	...	141.0	45.0	1038.0	176.0	0.842143	0.758065	0.444795	0.845752	0.677395	97
98	0.322259	520.0	147.0	4344.0	589.0	0.868571	0.779610	0.468891	0.873351	0.709748	...	135.0	43.0	1040.0	182.0	0.839286	0.758427	0.425867	0.845436	0.676897	98
99	0.321954	519.0	152.0	4339.0	590.0	0.867500	0.773472	0.467989	0.873516	0.710030	...	133.0	40.0	1043.0	184.0	0.840000	0.768786	0.419558	0.845649	0.678375	99

	model1
loss	0.351203
tp	274.000000
fp	85.000000
tn	2304.000000
fn	337.000000
accuracy	0.859333
precision	0.763231
recall	0.448445
auc	0.848190
prc	0.674599

	loss	tp	fp	tn	fn	accuracy	precision	recall	auc	prc	...	val_tp	val_fp	val_tn	val_fn	val_accuracy	val_precision	val_recall	val_auc	val_prc	epoch
0	0.669142	961.0	2042.0	4838.0	759.0	0.674302	0.320013	0.558721	0.690364	0.416909	...	221.0	427.0	656.0	96.0	0.626429	0.341049	0.697161	0.720127	0.435239	0
1	0.643501	680.0	1756.0	2735.0	429.0	0.609821	0.279146	0.613165	0.661389	0.352979	...	231.0	407.0	676.0	86.0	0.647857	0.362069	0.728707	0.742050	0.440918	1
2	0.618691	739.0	1633.0	2858.0	370.0	0.642321	0.311551	0.666366	0.709836	0.402931	...	226.0	362.0	721.0	91.0	0.676429	0.384354	0.712934	0.749832	0.444665	2
3	0.619396	695.0	1440.0	3051.0	414.0	0.668929	0.325527	0.626691	0.708558	0.384729	...	229.0	343.0	740.0	88.0	0.692143	0.400350	0.722397	0.753805	0.446564	3
4	0.615343	733.0	1426.0	3065.0	376.0	0.678214	0.339509	0.660956	0.719908	0.383918	...	232.0	343.0	740.0	85.0	0.694286	0.403478	0.731861	0.758139	0.449108	4
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
195	0.507905	774.0	894.0	3597.0	335.0	0.780536	0.464029	0.697926	0.827969	0.600445	...	222.0	206.0	877.0	95.0	0.785000	0.518692	0.700315	0.845031	0.682759	195
196	0.504511	761.0	852.0	3639.0	348.0	0.785714	0.471792	0.686204	0.830325	0.604347	...	218.0	203.0	880.0	99.0	0.784286	0.517815	0.687697	0.844835	0.682076	196
197	0.505772	767.0	885.0	3606.0	342.0	0.780893	0.464286	0.691614	0.827320	0.596544	...	220.0	197.0	886.0	97.0	0.790000	0.527578	0.694006	0.844741	0.681612	197
198	0.506922	776.0	855.0	3636.0	333.0	0.787857	0.475782	0.699730	0.828396	0.601541	...	219.0	197.0	886.0	98.0	0.789286	0.526442	0.690852	0.844738	0.681860	198
199	0.513123	757.0	872.0	3619.0	352.0	0.781429	0.464702	0.682597	0.823093	0.599388	...	221.0	199.0	884.0	96.0	0.789286	0.526190	0.697161	0.844441	0.681379	199

	model1	model2
loss	0.351203	0.472674
tp	274.000000	443.000000
fp	85.000000	450.000000
tn	2304.000000	1939.000000
fn	337.000000	168.000000
accuracy	0.859333	0.794000
precision	0.763231	0.496081
recall	0.448445	0.725041
auc	0.848190	0.846483
prc	0.674599	0.669177

	loss	tp	fp	tn	fn	accuracy	precision	recall	auc	prc	...	val_tp	val_fp	val_tn	val_fn	val_accuracy	val_precision	val_recall	val_auc	val_prc	epoch
0	0.862507	539.0	774.0	6106.0	1181.0	0.772674	0.410510	0.313372	0.607715	0.363548	...	0.0	0.0	1083.0	317.0	0.773571	0.000000	0.000000	0.618621	0.323339	0
1	0.815921	180.0	568.0	3923.0	929.0	0.732679	0.240642	0.162308	0.541993	0.223992	...	1.0	3.0	1080.0	316.0	0.772143	0.250000	0.003155	0.651280	0.349756	1
2	0.784625	241.0	709.0	3782.0	868.0	0.718393	0.253684	0.217313	0.558265	0.237985	...	10.0	10.0	1073.0	307.0	0.773571	0.500000	0.031546	0.673355	0.367656	2
3	0.778744	296.0	860.0	3631.0	813.0	0.701250	0.256055	0.266907	0.552279	0.237919	...	25.0	29.0	1054.0	292.0	0.770714	0.462963	0.078864	0.692885	0.381585	3
4	0.773754	336.0	1025.0	3466.0	773.0	0.678929	0.246877	0.302976	0.546982	0.240566	...	44.0	55.0	1028.0	273.0	0.765714	0.444444	0.138801	0.709392	0.391427	4
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
195	0.508968	724.0	713.0	3778.0	385.0	0.803929	0.503827	0.652840	0.832161	0.587092	...	211.0	177.0	906.0	106.0	0.797857	0.543814	0.665615	0.844998	0.675190	195
196	0.508318	713.0	757.0	3734.0	396.0	0.794107	0.485034	0.642922	0.833690	0.588169	...	212.0	178.0	905.0	105.0	0.797857	0.543590	0.668770	0.845122	0.675610	196
197	0.508781	729.0	766.0	3725.0	380.0	0.795357	0.487625	0.657349	0.833125	0.587219	...	212.0	176.0	907.0	105.0	0.799286	0.546392	0.668770	0.845729	0.676868	197
198	0.521313	708.0	755.0	3736.0	401.0	0.793571	0.483937	0.638413	0.826800	0.568646	...	211.0	174.0	909.0	106.0	0.800000	0.548052	0.665615	0.845724	0.677024	198
199	0.510027	719.0	737.0	3754.0	390.0	0.798750	0.493819	0.648332	0.829671	0.595413	...	210.0	172.0	911.0	107.0	0.800714	0.549738	0.662461	0.846033	0.677553	199